An instrument for spotting the next edtech opportunity — generated ideas, each traced to the real-world signals behind it.
The evidence library — the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2606.26901v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in multilingual and demographically diverse Indian healthcare context remains largely unknown. In this study, we first conduct the systematic audit of ASR performance on real-world psychiatric interview data spanning Kannada, Hindi and Indian English, comparing eight state-of-the-art models including IndicWhisper, WhisperLargeV3, Sarvam, GoogleS2T, Gemma3n, OmniLingual, Vaani, and Gemini. Our results reveal substantial variability across models and languages, with some systems performing competitively in Indian English but failing in regional speech. We further fine-tune two of the best performing opensource models, i.e., Gemma3n and OmniLingual, using various methods. With this, we uncover systematic performance gaps tied to speaker role and gender, raising concerns about equitable deployment in clinical settings, which are furthe
arXiv:2606.26880v1 Announce Type: new Abstract: Language-model representations provide structured, high-dimensional annotations of naturalistic language stimuli and can serve as informative neural predictors during comprehension. We analyzed locked derived data from Brain Treebank, MEG-MASC, and Podcast ECoG with eight frozen language models, blocked encoding models, and matched temporal, nuisance, and representation-capacity controls. Positive held-out prediction and gains over low-level baselines were widespread in source-level summaries. Across Brain Treebank and Podcast ECoG, 67 of 432 evaluable rows met a controlled predictive-only criterion, and model-side feature ablations changed prediction scores in most evaluable source rows. Brain-derived, timing-linked, acoustic, and implanted-signal controls confirmed component-level sensitivity of the analysis pipeline. These findings show that language-model-derived quantities can annotate neural activity during natural speech and text c
arXiv:2606.26875v1 Announce Type: new Abstract: Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages. Existing KV cache compression methods mainly rely on attention weights to estimate token importance. While attention effectively captures contextual relevance, it overlooks complementary information-theoretic signals related to predictive uncertainty and token informativeness. In this paper, we revisit token importance from a forward-looking perspective and introduce \textit{Forward Influence}, a metric that measures how compressed tokens affect future contexts. Our analysis reveals that tokens selected by attention scores mainly influence nearby contexts, whereas tokens associated with high predictive uncertainty exhibit substantially stronger influence on distant future contexts. Based on the observation, we propose \textbf{InfoKV}, an entropy-aware KV cache compression
arXiv:2606.26861v1 Announce Type: new Abstract: Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands extreme compression, yet existing structured pruning methods collapse at high compression ratios due to one-shot importance estimation, and their cross-architecture behavior remains unpredictable. This article presents a cascaded multi-granularity pruning framework that removes layers, attention heads, and feed-forward channels in coarse-to-fine order, with lightweight low-rank recovery between stages to re-estimate component importance. An information-theoretic analysis motivates this ordering, and the Structural Independence Assumption (SIA) is formalized as a checkable condition predicting whether per-component pruning criteria are reliable for a given architecture: Multi-Head Attention (MHA)+GELU designs satisfy the SIA, whereas Grouped Query Attention (GQA)+SwiGLU designs violate it. On bearing fault diagnosis spanning 88M to 6.25B-par
arXiv:2606.26819v1 Announce Type: new Abstract: This paper describes our submission to the IWSLT 2026 Instruction Following shared task. SpeechLLMs are developed for both short-form and long-form speech instruction following under constrained settings. For the short track, strong performance is achieved on MCIF, with a SIFS score of 2.0708. For the long track, three speech segmentation methods are explored, and the HIFS score is introduced to account for unstable long-form generation. Experimental results show that fixed 30-second segmentation provides the most robust long-form performance, achieving the highest HIFS score of 2.0663. Further analysis shows that hallucination mainly manifests as repetitive insertions in generated outputs, substantially affecting ASR and SSUM, while short-form capabilities are largely retained after long-form extension.
arXiv:2606.26803v1 Announce Type: new Abstract: We present a computational corpus study of vocabulary relationships across eight tradition layers of Bengali and Sanskrit devotional literature spanning the 8th to 19th centuries, encompassing Buddhist Vajrayana, Shakta Tantra, Vaishnava, and Baul traditions. Using a corpus of 75 texts and TF-IDF character n-gram vectorization with cosine similarity analysis, we address the historically argued but previously unquantified claim that Buddhist Vajrayana vocabulary survived the collapse of the Pala monasteries and was absorbed into the Shakta Tantra tradition of Bengal. The central finding is a specificity result: the Gitagovinda (Vaishnava Sanskrit, 12th century) has zero cosine similarity to Shakta Kali texts, while Bridge Tara texts (Buddhist-Shakta transitional, same century, same language) have cosine similarity 0.54 to Shakta Kali. This 8.5-fold contrast between two Sanskrit traditions from the same century demonstrates that the Buddhis
arXiv:2606.26790v1 Announce Type: new Abstract: Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermediate decisions should be reinforced or suppressed. On-policy self-distillation offers dense token-level supervision, yet existing skill-conditioned variants often rely on external skill memories or retrieved privileged context, which are costly to maintain and can be mismatched with the state distribution induced by the current policy in multi-turn interaction. We propose \textbf{OPID} (\textbf{O}n-\textbf{P}olicy Sk\textbf{i}ll \textbf{D}istillation), a framework that extracts skill supervision directly from completed on-policy trajectories. OPID represents trajectory hindsight as hierarchical skills: episode-level skills capture global workflows or failure-avoidance rules, while step-level skills capture local decision knowledge at critical timesteps. A critica
arXiv:2606.26775v1 Announce Type: new Abstract: Multimedia event extraction aims to jointly identify events and their arguments across multiple modalities, such as text and images, to support more comprehensive event understanding. While recent work reports steady and substantial progress, the reliability and comparability of these results critically depend on consistent and rigorous evaluation. In this work, we present the first systematic analysis of evaluation pitfalls in multimedia event extraction and identify three major sources of issues: inconsistent data processing, inconsistent task assumptions, and overly relaxed evaluation settings. We demonstrate, through a series of controlled experiments under a strict evaluation framework, that minor evaluation choices can cause large performance variations and lead to overestimation of a model's ability to ground real-world events across modalities. Our findings highlight the need for comparable evaluation standards and encourage a shi
arXiv:2606.26753v1 Announce Type: new Abstract: Conversational memory retrieval optimizes relevance, yet a retrieved memory can be relevant and simultaneously outdated: a later turn updates, corrects, or supersedes it. ConvMemory v3 adds a validity context layer that detects and surfaces this update evidence through target-conditioned relation verification, sitting after the v1/v2 retrieval path. The core mechanism is a dual-evidence gate that conditions a relation judgment on the specific target proposition, scoring a (target, source) pair through the product of a MiniLM slot head and a DeBERTa-v3 slot head and gating it by conservative event/operation evidence. On a synthetic multi-hop validity benchmark the gate reaches 90.12% +/- 1.73 accuracy; through a real-data feedback loop that mines failure patterns but trains on synthetic pairs only, the verifier transfers to Memora role binding with zero target-side labels, reaching 98.8% +/- 0.9 group-all-correct. The deployed layer preser
arXiv:2606.26698v1 Announce Type: new Abstract: In today's fast-paced information era, logical fallacies, defined as defective patterns of reasoning, inevitably contribute to the growth of information disorder. However, often fallacies appear in nuanced forms that complicate automated classification. In this study, we investigate whether merging abstract logical structures with context-level linguistic cues proves beneficial for fallacy classification, developing a framework that inductively extracts such patterns from fallacious examples and their explanations using Large Language Models (LLMs). We evaluate the impact of these patterns across different LLMs and experimental zero- and one-shot configurations, showing statistically significant improvements over zero-shot baselines and outperforming competing approaches. Cross-dataset experiments validate generalization, establishing data-driven pattern extraction as an effective method for generating logical representations.
arXiv:2606.26654v1 Announce Type: new Abstract: Personalized language-model assistants are often evaluated through a memory lens: can a model recall preferences users have explicitly stated in dialogue? More comprehensive personalization demands a harder capability -- inferring what users care about from the multimodal traces they naturally leave behind. We introduce SocialPersona, a benchmark for evaluating whether multimodal large language models (MLLMs) can recover revealed preferences from longitudinal social-media timelines and use them in dialogue. Built from longitudinal timelines of 171 everyday, non-promotional social-media users, SocialPersona contains text, images, timestamps, and 2,597 human-verified preference tags across seven interest domains, separating stable interests from recent interests. It supports two tasks: constructing structured user profiles from multimodal context and generating responses aligned with inferred profiles. Experiments with proprietary and open-
arXiv:2606.26650v1 Announce Type: new Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes. It has two key components, learnable modulation (LM) and softened ternarization (ST), which are coupled from an optimization perspective. LM leverages a composition of learnable factors to modulate the distribution of pre-trained high-precision weights and the ternary threshold, making them less sensitive to ternarization. ST further introduces a differentiable transition function to guide the ternarization process toward stable convergence. We show that, for pre-trained LLMs with 1.7B to 8B parameters, CAT
arXiv:2606.26618v1 Announce Type: new Abstract: Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B-parameter, tokenizer-free TTS model that joins a MiniCPM-4 language-model backbone with a flow-matching diffusion decoder. We build one shared, language-tagged corpus of about 26 hours and adapt VoxCPM2 with a single Low-Rank Adaptation (LoRA) adapter, trained on both languages at once and added to both the language model and the decoder. The adapter is zero-initialized, so training starts exactly at the original (zero-shot) model. In native-speaker listening tests, the Khmer Mean Opinion Score (MOS) rises from 3.85 to 4.23 with the best adapter (rank 64), a highly significant gain (paired Wilcoxon test, p<0.001), while training only 0.19 to 3.03 percent of the parameters. The automatic loss and the human ratings
arXiv:2606.26571v1 Announce Type: new Abstract: Zero-shot tweet-level stance detection confronts two primary challenges: (1) mitigating the context sparsity inherent in short texts, and (2) establishing the relevance between implicit targets and textual content. While existing methods primarily focus on incorporating external knowledge, they neglect the intrinsic semantic cues embedded within key intra-textual entities. Furthermore, current models exhibit limited capability in determining the relevance of unseen targets to the given text, thereby struggling to differentiate between "neutral" and "irrelevant" stance labels. To address these issues, we first construct a four-class, multi-topic Japanese tweet dataset. To our knowledge, this is the first Japanese tweet-level dataset for stance detection. We then propose KIRP, a zero-shot stance detection framework. It integrates external knowledge with entity reorganization for data augmentation and employs prompt chaining for reasoning. S
arXiv:2606.26560v1 Announce Type: new Abstract: Delta-rule linear attention improves recurrent memory updates by correcting what is already stored at the current write address before writing new content. However, the active correction is still anchored to that same write address. As a result, stale information stored at a different address cannot be actively removed before new content is written elsewhere. We propose Erase-then-Delta Attention (EDA), a memory update rule that decouples where to erase from where to write. The key insight is that recurrent memory models should not only correct the current write, but also selectively suppress outdated memory at an independently chosen address. Concretely, our method first applies a targeted erase step along a learned erase direction, and then performs the standard delta-style corrective write along the current write direction. This preserves the corrective behavior of delta-rule updates while expanding their memory-management capacity. La
arXiv:2606.26530v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus (ARC;~\citealp{chollet2019measure}) contains tasks that require summarizing patterns from limited grid samples and predicting output grids. Recently, many large language model based approaches have attempted to transform it into a text-based reasoning task. However, methods based on open-source models have generally yielded unsatisfactory results, while those relying on closed-source models are too costly. Current efforts mainly focus on data augmentation, constructing ARC-like data for more comprehensive supervised fine-tuning. In this work, we argue that solving ARC-like problems requires not only \textit{positive} sample supervision but also the ability to improve model reasoning by distinguishing \textit{negative} samples. To this end, we draw on the idea of preference alignment and propose \textsc{DiARC}, a method that constructs preference pairs to enable the model to distinguish between them. Sp
arXiv:2606.26529v1 Announce Type: new Abstract: AI safety is evaluated by how reliably a model detects the hazards it is told to find, yet accidents often arise from the hazard no one specified. We show that conditioning a language or vision model on a narrow task suppresses its reporting of co-present, safety-critical signals it can otherwise report, a machine analogue of human inattentional blindness arising from a different mechanism. Across radiology and driving text scenarios and chest-radiograph vision tasks, suppression appeared in every model tested, did not diminish with scale, persisted in a reasoning model, and varied more by model family than by size, while the same models reported these signals at substantially higher rates when unconstrained. We name this dissociation the Inattentional Gap and argue that it decouples measured benchmark safety from real-world safety: a system can score near-perfectly on the hazards an evaluation specifies while remaining blind to those tha
arXiv:2606.26522v1 Announce Type: new Abstract: While corporate narrative disclosures provide crucial information to capital markets, comprehensively evaluating their qualitative changes over time remains challenging. Narrative text is inherently multidimensional, meaning that an improvement in one textual dimension often occurs alongside changes in others. To capture these underlying dynamics, we propose a longitudinal text analysis approach combining Japanese-language NLP metric extraction with paired testing, shift function analysis, and inter-metric correlation. Our framework extends prior indicator sets by incorporating a cross-section relevance indicator to measure topical alignment between risk disclosures and management strategies. Applying this approach to evaluate Japan's 2019 disclosure reforms, we analyze 19,770 firm-year observations over a 10-year period (FY2015-FY2024). The joint analysis reveals complex shifts in disclosure patterns that are frequently masked by convent
arXiv:2606.26511v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time. When a fact changes (e.g., a function is renamed or API restructured), RAG retrieves both the stale and current value with near-identical embedding similarity. The agent then either abstains or serves the superseded fact. We show this is a structural problem: on a calibrated dataset, cosine similarity distinguishes a contradicted fact from a duplicated one with AUROC 0.59 (near chance), as contradictions are often more embedding-similar to the original than rephrased duplicates. We present MemStrata, a retrieval memory maintaining temporal validity. It stores facts like RAG, preserving static recall, but when a fact's value is contradicted, a deterministic (subject, relation, object) supersession rule retires the stale value in a bi-temporal ledger - with no similarity threshold and no LLM call. Across six benchmarks run locally wi
arXiv:2606.26493v1 Announce Type: new Abstract: Diffusion language models offer a promising alternative to autoregressive models due to their potential for parallel and iterative generation. However, existing approaches use a single network for both context representation and iterative denoising, forcing one model to serve both roles and limiting its capacity for either role. We propose TwoTower, a block-wise autoregressive diffusion model that decouples these roles into two towers: a frozen AR context tower that causally processes clean tokens, and a trainable diffusion denoiser tower with bidirectional block attention that refines noisy blocks via cross-attention to the context. Built on Nemotron-3-Nano-30B-A3B, an open-weight 30B hybrid Mamba-Transformer MoE model, and trained on approximately 2.1T tokens, Nemotron-TwoTower retains 98.7% of the autoregressive baseline's quality while offering 2.42X higher wall-clock generation throughput. We release the code and model weights at htt
arXiv:2606.26489v1 Announce Type: new Abstract: News media play a central role in shaping public perceptions of climate change, and whether coverage emphasizes threats or solutions has measurable effects on audience engagement and policy support. Automated detection of these framing patterns at the sentence level would allow researchers to analyze large corpora that are infeasible to code manually. We present a systematic comparison of two approaches for classifying sentences from German-language climate news articles as threat-oriented, solution-oriented, both, or neither. The first approach uses few-shot prompting with an open-weights large language model (Llama 4 Maverick), employing chain-of-thought reasoning and structured output with confidence scoring. The second approach fine-tunes a German BERT model (deepset/gbert-large) for sentence-pair classification, where the preceding sentence provides contextual information for the target sentence. Both approaches implement two indepen
arXiv:2606.26487v1 Announce Type: new Abstract: Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet their discrete, language-oriented tokenization and embedding interfaces are misaligned with continuous numerical values, often harming numerical ordering and forecasting reliability. We propose TempoWave, a plug-and-play temporal wavelet digit interface that maps each scalar observation into digit-wise embeddings constructed from multi-wavelet, multi-scale coefficients. By directly overriding standard token representations, TempoWave seamlessly exposes both fine-grained local fluctuations and macro global structures in a transformer-compatible form, ensuring that precise numerical formatting, distinct digit identity, and robustness to common normalization operations are maintained throughout the LLM pipeline. Experiments across five context-enriched forecasting benchmarks demonstrate that Temp
arXiv:2606.26481v1 Announce Type: new Abstract: Billions of scientific papers lead to the need to identify essential parts from the massive text. Scientific research is an activity from putting forward problems to using methods. To learn the main idea from scientific papers, we focus on extracting problem and method sentences. Annotating sentences within scientific papers is labor-intensive, resulting in small-scale datasets that limit the amount of information models can learn. This limited information leads models to rely heavily on specific forms, which in turn reduces their generalization capabilities. This paper addresses the problems caused by small-scale datasets from three perspectives: increasing dataset scale, reducing dependence on specific forms, and enriching the information within sentences. To implement the first two ideas, we introduce the concept of formulaic expression (FE) desensitization and propose FE desensitization-based data augmenters to generate synthetic data
arXiv:2606.26466v1 Announce Type: new Abstract: Multilingual large language models often produce inconsistent reasoning and answers for semantically equivalent prompts in different languages. Prior work suggests that intermediate representations can be relatively language-agnostic, but generation becomes increasingly language-specific as models commit to discrete output tokens. This is problematic because language-specific lexical choices can cause semantically equivalent reasoning paths to diverge across languages. These divergences motivate searching for a cross-lingual alignment signal that is less tied to any single vocabulary item or script. We propose SOLAR, an auxiliary objective for supervised fine-tuning that aligns soft-token representations across languages, using English as a pivot. Soft tokens are probability-weighted mixtures over the vocabulary embeddings, yielding continuous representations that can aggregate information from semantically related tokens across languages
arXiv:2606.26452v1 Announce Type: new Abstract: To minimize privacy concerns and inference latency on edge devices like smartphones, lightweight on-device models remain important for end-user applications. Many of these applications involve natural language classification, but deploying multiple specialized models creates a memory footprint challenge. We investigate: Can a single lightweight architecture solve multiple Speech-Adjacent (SA) classification tasks through reduction to a nuanced text similarity formulation? We propose AnySimLite, a lightweight similarity encoder that combines word-level and character-level channels. Together with a dataset transformation strategy, we evaluate AnySimLite across multiple SA classification tasks and show that it consistently achieves state-of-the-art (SOTA) or SOTA-competitive performance in few-shot settings while maintaining a low memory footprint. Even in the worst case, the performance drop remains below 7% while using $<\frac{1}{250}^{\ma
arXiv:2606.26449v1 Announce Type: new Abstract: Retrieval-augmented systems routinely present citations alongside generated answers, yet a citation does not confirm that the corresponding source meaningfully shaped the output. This paper introduces ProvenAI, a framework that decomposes transparency in multi-hop question answering into three independently measurable layers: answer correctness, citation fidelity against benchmark supporting evidence, and per-document influence under leave-one-resource-out intervention. Targeting the HotpotQA distractor benchmark through a seven-stage pipeline covering data normalisation, retrieval indexing, citation-aware answer generation, attribution auditing, ablation-based influence estimation, batch evaluation, and interactive inspection, ProvenAI evaluates 7,405 validation examples drawn from a canonical corpus of 509,300 passages. The system achieves 53.53% answer accuracy alongside a mean citation-fidelity score of 71.55%, and a worked example su
arXiv:2606.26437v1 Announce Type: new Abstract: Existing metrics for factuality and faithfulness evaluate whether an answer is supported or contradicted by its grounding documents, but they fail to capture when both supporting and contradicting evidence coexist. We introduce ConflictScore, a novel metric that quantifies how well a model's response acknowledges conflicting evidence in its grounding documents. Our framework decomposes responses into atomic claims, labels each claim against each grounding document, and then aggregates these labels into two complementary measures: ConflictScore-Count (CS-C), the proportion of claims exhibiting conflicts, and ConflictScore-Ratio (CS-R), the balance between supporting and contradicting evidence. We develop ConflictBench, a benchmark covering diverse forms of conflicts such as ambiguity, contradiction, and divergent opinions, to systematically evaluate our metric. Experiments show that ConflictScore effectively detects overconfident claims ac
arXiv:2606.26403v1 Announce Type: new Abstract: Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longitudinal updates. Real user data is difficult to share, perturb, audit, or redistribute responsibly, while independently generated fake fields rarely preserve the cross-field and temporal consistency needed for controlled evaluation. We present PROFILEFOUNDRY, a deterministic generator and fixed reference release of 100,000 adult synthetic Person Objects across eight locales. Each object combines a typed current snapshot, household, family, and employer links, snapshot-aligned events, normalized relational views, and generation provenance. The release contains 709,228 events, 40,338 households, 52,491 employers, and 518,564 directed relationship edges. We report evidence in separate categories: selected population-marginal comparisons, per-object invariant checks, release-wide referential a
arXiv:2606.26360v1 Announce Type: new Abstract: The neutral, or floating, tone of Mandarin Chinese is a tone with an enigmatic set of properties. It has been described as a reduced tone, or as a tone that sometimes is lexically fixed but that can also be toneless. In two-syllable words, it is found only on the second syllable, but single-syllable words can also have the neutral tone. We present a corpus-based study of the phonetic realization of the neutral tone in spontaneous conversational speech corpora of Beijing Mandarin and Taiwan Mandarin. We show that the neutral tone has its own tonal target, just as the four lexical tones of Mandarin. We also show that disyllabic words with a neutral tone have pitch contours that have a pitch component that depends on the tone on the first syllable, just as has been observed for two-syllable words with a lexical tone on the second syllable (Chuang et al., 2026). Furthermore, words with a floating tone have word-specific pitch signatures, whic
arXiv:2606.26196v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently made remarkable progress in unifying vision-language understanding and reasoning, especially following the introduction of models such as OpenAI's O-series and DeepSeek's R-series, which have driven a paradigm shift toward perception-centric intelligence. However, there remains a lack of systematic surveys that examine perception from a truly unified vision-language perspective -- one that treats vision and language as an inseparable modality. Existing reviews are often fragmented, focusing separately on either vision or language, and thus rarely capture the cross-modal evolution of perception as an integrated capability. To bridge this gap, we present the first systematic survey of unified vision-language perception in MLLMs. Specifically, we (1) formalize MLLM perception as an intrinsic, unified vision-language capability analogous to human innate perception, (2) introduce a five-st
arXiv:2606.26130v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to guide research methodology, yet their default methodological tendencies under minimal prompting remain unclear. Here, we prompt GPT-5.1, Gemini 3 Pro, and DeepSeek-V3.2 with an LLM-extracted research question from each of 1,000 recent arXiv computer-science papers and compare the resulting methodology suggestions against a paper-derived experimental inventory. Since we provide only the research question, the differences we measure reflect initial suggestions and not how optimal those suggestions are. We extract structured method features from both sources, map them into a shared taxonomy, and quantify divergence across multiple taxonomy dimensions including model provider, dataset task type, and evaluation metric type. The strongest imbalance appears in provider choice, with Jensen-Shannon divergence about 3-5x larger than any other taxonomy dimension. Other/Academic single-occurrence
arXiv:2606.26120v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms. However, their computational complexity scales on the order of L cubed with the sequence length L. This poses significant challenges for long-sequence and real-time applications, primarily due to the lack of compatibility with key-value caching and the non-autoregressive nature of denoising steps. Existing acceleration methods rely on static caching or parallel decoding strategies, which fail to account for the dynamic behavior of token properties across layers and decoding steps. We propose Dynamic-dLLM, a training-free framework that enhances dLLM inference efficiency through two components: Dynamic Cache Updating (DCU), which adaptively allocates cache-update budgets based on layer-wise token dynamics, and Adaptive Parallel Decoding (APD), which dynamically c
arXiv:2606.26112v1 Announce Type: new Abstract: Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training corpora. We present a systematic methodology for transforming structured linguistic resources into specialized AI systems, demonstrating that expert-curated lexical databases can serve as effective foundations for conversational AI development. Our approach converts Hindi WordNet into 1.25 million diverse instruction-response pairs, fine-tunes a 12B-parameter language model using resource-efficient LoRA with 4-bit quantization. Evaluation through a Hindi language learning chatbot demonstrates that structured-knowledge-based systems achieve superior pedagogical effectiveness (91.0 vs. 79.4-83.6 for general-purpose models) while maintaining competitive semantic performance and exceptional consistency. The complete pipeline demonstrates a proof-of-concept methodology using Hindi for developing spe
arXiv:2606.26108v1 Announce Type: new Abstract: Larger language models consistently outperform smaller ones on reasoning benchmarks, yet the reasoning differences underlying this gap remain underexplored. Across benchmarks in mathematics, physics, chemistry, and programming, we observe stable performance gaps: averaged over datasets, Qwen3-32B outperforms Qwen3-8B by 6.43%, while GPT-OSS-120B exceeds GPT-OSS-20B by 7.38%. To study the reasoning differences behind these gains, we develop AdvCluster, an automated framework that identifies questions where the larger model shows a stable advantage, extracts fine-grained advantage descriptions from paired reasoning traces produced by larger and smaller models, and organizes them through semantic clustering with quantitative evaluation and selection guided by a reviewer model. Our analysis yields a systematic taxonomy of larger model reasoning advantages, spanning both common advantages that recur across domains and specialized advantages as
arXiv:2606.26107v1 Announce Type: new Abstract: Sign language communication systems, that integrate emotional expression remain underexplored, particularly for low-resource languages. This pilot study presents NEST-V1 (Nepali Emotion and Speech Transformer - Version 1), a proof-of-concept multimodal framework that demonstrates the feasibility of generating emotion-conditioned Nepali Sign Language avatars from spoken input. As a preliminary investigation, we focus on four common Nepali words ("thank you", "hello", "house", "me") across three emotional states (happy, neutral, sad) to validate our core technical approach. Our lightweight architecture employs a shared acoustic encoder for simultaneous Automatic Speech Recognition and emotion classification, achieving 81.1% ASR accuracy and 79.21% emotion recognition accuracy on a dataset of 600 labeled audio samples from 50 speakers. The system demonstrates 37% parameter efficiency compared to separate model architectures while maintaining
arXiv:2606.26106v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in emotionally charged situations involving interpersonal conflict, frustration, and distress. While prior safety research has focused on preventing explicit harms such as toxic or policy-violating content, less attention has been paid to conversational behaviors that may unintentionally escalate conflict. In this paper, we investigate whether LLMs can be guided toward more de-escalating dialogue behavior through lightweight prompt-level constraints derived from Nonviolent Communication (NVC). We reformulate NVC principles as process-oriented guidelines that discourage blame attribution, emphasize attention to users' emotional experiences, and encourage clarification before advice. Using a dual-agent simulation framework across multiple instruction-tuned models and user resistance levels, we show that NVC-constrained prompting consistently reduces conversational escalation and stabilizes
arXiv:2606.26105v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong capabilities in short-context reasoning but degrade in performance over long conversational horizons due to context window limitations and inefficient token usage. We introduce ContextForge, a system for context recycling that maintains task-relevant information across turns by combining structured query generation, external memory retrieval, and controlled synthesis. The system enables efficient reuse of prior computation without relying on full context replay, reducing token overhead while preserving answer quality. We evaluate ContextForge using a 15-turn conversational benchmark that tests multi-turn reasoning, back-references, and domain shifts across structured healthcare queries. Compared to a baseline agent using identical underlying models, ContextForge demonstrates improved consistency and reduced token consumption, while maintaining comparable response accuracy. These results suggest
arXiv:2606.26104v1 Announce Type: new Abstract: Animal-welfare advocates produce a lot of writing, and increasingly that writing trains the language models that millions of people then ask about animal welfare. Using vocabulary-matched stance-contrast probes on a held-out animal-welfare benchmark, we measure how each of ten linguistic features changes Llama-3.2-1B's preference for pro-animal-welfare reasoning when used as fine-tuning data. Eight of the ten features produce statistically significant shifts. Seven move the model toward stronger pro-animal-welfare reasoning: assertive certainty, explicit moral vocabulary, emotion words, evaluative claims, narrative structure, depicted harm severity, and immediate temporal framing. Two move it the other way: hedged language and concrete sensory description both dilute the pro-animal-welfare stance. First-person perspective has no statistically significant effect. The practical recommendation for anyone writing animal-welfare text that may
arXiv:2606.26103v1 Announce Type: new Abstract: Large Language Models (LLMs) have rapidly influenced many aspects of society, particularly education, due to their demonstrated ability to complete assignments and examinations across a wide range of subjects. Although prior studies have examined the educational impact of LLMs, much of the existing work relies on public or open problem datasets and lacks topic-specific analysis. In engineering education, especially within mechanical engineering, systematic investigations of LLM performance on specific problem types remain limited. Instead of using traditional methods that directly ask textbook questions to an LLM tool, our study adopts a model distillation process to evaluate LLM capabilities in solving statics problems. By distilling ChatGPT, we extracted 25 text-only statics questions and further constructed two additional datasets by adding diagrams and modifying their numerical values. Experimental results show that while LLMs perform
arXiv:2606.26101v1 Announce Type: new Abstract: Reliable evaluation of large language models should separate supported answering from unsupported guessing without conflating either with data contamination, prompt idiosyncrasy, or generic refusal behavior. We present a contamination-aware, multi-zone benchmark for measuring the transition from answerable knowledge to abstention-expected unknowns under frozen build-time labels. The benchmark contains 1,200 items across five domains, explicit abstention expectations, contamination-risk metadata, and dual parsing with an official strict parser plus a normalized robustness parser. We evaluate FLAN-T5, Qwen2.5-Instruct, and Llama-3-Instruct models under locked answer-or-abstain prompts, answer-only controls, and prompt-template variants. The benchmark is not solved by generic non-answer behavior: FLAN baselines remain weak on productive abstention, while stronger instruction-tuned models expose a selective but incomplete transition from answ
arXiv:2606.26100v1 Announce Type: new Abstract: Media bias detection is a critical task for ensuring fair and balanced information dissemination, yet existing sentence-level approaches classify each sentence independently, ignoring inter-sentence contextual signals that human annotators naturally exploit. We present \textbf{HierBias}, a hierarchical context-conditioned media bias detector that formally models document context in bias prediction. We introduce the \emph{context-conditioned bias probability} and prove theoretically that leveraging document context strictly reduces the Bayes error of sentence-level classification when inter-sentence mutual information is non-zero. A multi-task generalization bound further establishes that jointly training binary bias detection and fine-grained bias type classification improves sample efficiency on small annotated corpora. Architecturally, HierBias pairs a sentence-level RoBERTa encoder with a cross-sentence Transformer aggregator and dual
arXiv:2510.26518v2 Announce Type: replace-cross Abstract: Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can leverage AI to improve the quality of human oversight. We focus on an important safety problem that is already challenging for humans: fact-verification of AI outputs. We find that combining AI ratings and human ratings based on AI rater confidence is better than relying on either alone. Giving humans an AI fact-verification assistant further improves their accuracy, but the type of assistance matters. Displaying AI explanation, confidence, and labels leads to over-reliance, but just showing search results and evidence fosters more appropriate trust. These results have implications for Amplified Oversight -- the challenge of combining humans and AI to supervise AI systems even as they surpass hu
arXiv:2606.09843v2 Announce Type: replace Abstract: Large language models (LLMs) give stable answers to personality questionnaires, yet these self-reports fail to predict how the models actually behave. Is this gap an artifact of forcing human trait categories onto LLMs, or something deeper about LLM self-report itself? To find out, we built the first psychometric instrument whose dimensions are derived bottom-up from LLM behavior rather than borrowed from human psychology. Administering 300 items (240 Likert + 60 scenario) to 25 LLMs across 17 model families, 30 times each, exploratory factor analysis revealed five replicable, highly reliable factors: Responsiveness, Deference, Boldness, Guardedness, and Verbosity (all Tucker $\phi \geq .957$, all $\alpha \geq .930$). We then collected 2,500 open-ended behavioral samples and had them rated by 151 humans and a three-judge LLM ensemble. Humans and judges agreed about model behavior ($\bar{r} = .51$), but self-report predicted neither: t
arXiv:2604.03501v5 Announce Type: replace Abstract: Experimental evidence suggests that AI tools raise worker productivity, but also that sustained use can erode the expertise on which those gains depend. To explore the consequences of this tradeoff, we develop a dynamic model in which a decision-maker chooses AI usage intensity for a worker over time, trading immediate productivity against the erosion of worker skill. We decompose the tool's productivity effect into two channels, one independent of worker expertise and one that scales with it. The model produces three main results. First, a decision-maker who fully anticipates skill erosion still rationally adopts AI when front-loaded gains outweigh long-run skill costs, lowering long-run productivity. The decomposition sorts deployments into five regimes by their long-run effect, separating beneficial from harmful adoption. Second, the tradeoff introduces the potential for misaligned incentives. When the decision-maker does not bear
arXiv:2604.01741v2 Announce Type: replace Abstract: Modeling users' cognitive states (e.g., cognitive load and decision confidence) is essential for building adaptive AI in high-stakes decision-making. While eye tracking provides non-invasive behavioral signals correlated with cognitive effort, prior work has not systematically examined how AI assistance contexts, specifically varying advice reliability and user heterogeneity, can alter the mapping between gaze signals and cognitive states. We conducted a within-subject lab eye-tracking study (N=54) on factual verification tasks under three conditions: No-AI, Correct-AI advice, and Incorrect-AI advice. We analyze condition-dependent changes in self-reports and eye-tracking patterns and evaluate the robustness of eye-tracking-based user modeling. Results show that AI advice increases decision confidence compared to No-AI, while Correct-AI is associated with lower perceived cognitive load and more efficient gaze behavior. Crucially, pred
arXiv:2601.00570v2 Announce Type: replace Abstract: Cognitive reappraisal is a well-studied emotion regulation strategy that helps individuals reinterpret stressful situations to reduce their impact. Many digital mental health tools struggle to support this process because rigid scripts fail to accommodate how users naturally describe stressors. This study examined the feasibility of an LLM-based single-session intervention (SSI) for workplace stress reappraisal. We assessed short-term changes in stress-related outcomes and examined design tensions during use. We conducted a feasibility study with 100 employees at a large technology company who completed a structured cognitive reappraisal session delivered by a GPT-4o-based chatbot. Pre-post measures included perceived stress intensity, stress mindset, perceived demand, and perceived resources. These outcomes were analyzed using paired Wilcoxon signed-rank tests with correction for multiple comparisons. We also examined sentiment and s
arXiv:2509.05219v5 Announce Type: replace Abstract: Conversational AI systems are increasingly being used in place of traditional search engines to help users complete information-seeking tasks. This has raised concerns in the political domain, where biased or hallucinated outputs could misinform voters or distort public opinion. However, in spite of these concerns, the extent to which conversational AI is used for political information-seeking, as well the potential impact of this use on users' political knowledge, remains uncertain. Here, we address these questions: First, in a representative national survey of the UK public (N = 2,499), we find that in the week before the 2024 election as many as 32% of chatbot users - and 13% of eligible UK voters - have used conversational AI to seek political information relevant to their electoral choice. Second, in a series of randomised controlled trials (N = 2,858 total) we find that across issues, models, and prompting strategies, task-direc
arXiv:2606.27258v1 Announce Type: cross Abstract: A core principle of object orientation -- that the functionality of a system can be partitioned amongst objects that correspond to individuals in the problem domain -- has influenced how software has been specified, designed and implemented for more than fifty years. Later developments in software engineering sought to build on this principle. But in fact this partitioning is neither natural nor straightforward, and the problems that these later developments sought to mitigate -- the fragmentation and conflation of functionality -- were often, in fact, the inevitable consequences of this founding principle. An easier path to addressing these problems therefore starts by going back, abandoning object orientation, and replacing it with an alternative approach that decouples the individuals of the problem domain from the modules that partition functionality.
arXiv:2606.26842v1 Announce Type: cross Abstract: Labeling speaker diarization data is costly, yet annotation tools rarely measure that cost. We present voxmap-studio, an open-source, React-based diarization annotation tool integrated with the pyannote-based diarization ecosystem. Its canvas is initialized by a fast stride-accelerated diarization engine so that the annotator corrects a hypothesis rather than drawing every speaker turn by hand, and the tool records annotation cost - typed edit-operation counts and time - as a first-class output, enabling quantitative comparison of how much different forms of assistance actually help. Export is gated on per-segment human confirmation and guarded by injected "phantom" attention checks, which prevent unverified automatic output from being released as ground truth. In a preliminary study on nine AMI audio files, unassisted manual annotation was the costliest and least accurate, and automatic initialization shifted the work from creating tur
arXiv:2606.26721v1 Announce Type: cross Abstract: AI coding agents are changing the bottleneck in software collaboration: code is increasingly cheap, while understanding intent, negotiating scope, and governing long-term project responsibility remain costly. This paper proposes \emph{Knowledge-Based Pull Requests} (KPR), a trusted workflow for agent-mediated software collaboration across trust boundaries, including open source, enterprise, vendor, contractor, and customer-driven settings. In KPR, an external collaborator's local code, tests, and cleaned agent interaction trace are treated as knowledge sources rather than as the default merge candidate. Agents distill these sources into a human-confirmed knowledge package and render it into reviewer-facing forms such as design memos, risk checklists, test plans, or implementation briefs. A project-owned inner trusted coding agent then regenerates candidate code inside the receiving project's environment under repository context, enginee