Papers

Prior case retrieval (PCR) aims to identify precedent cases relevant to a given query case. Existing PCR benchmarks and methods predominantly operate at the document level, treating entire judgments as the unit of relevance. This formulation is suboptimal for legal practitioners, as judgments address multiple legal issues and only a small subset of paragraphs is relevant to a particular query. Addressing this gap, we introduce UK-PRBench, a benchmark for paragraph-level precedent retrieval in UK case law, constructed from judgments obtained from the UK National Archives and covering a broad range of UK courts and tribunals. Furthermore, we evaluate state-of-the-art retrieval models and establish baseline results. Our experiments show that paragraph-level precedent retrieval remains challenging for current retrieval approaches, highlighting substantial room for improvement. UK-PRBench provides a standardised benchmark for evaluating fine-grained precedent retrieval and advancing retrieval systems for the UK legal domain.

Computational social science increasingly relies on large language models for text annotation, and the validity of published findings now rests on the labels generated by such models. Decision models, a new model class built for categorical question answering, answer typed questions with a choice, a probability distribution over the label set, and a confidence score rather than free text, at a small fraction of frontier inference prices. Whether their answers are accurate, and whether that stated confidence can be trusted on social science constructs, are unknown. Here, we mirror the evaluation of Ziems et al. (2024) on 18 computational social science classification tasks (7,977 items), comparing the first commercial decision model and two open-weight counterparts against 19 frontier and open-weight language models under the same zero-shot protocol, and extending the decision-model comparison to eleven open-weight systems released in the week after it. The decision model trails the per-task best LLM on 14 of 15 evaluation tasks, with a median deficit of 11.6 macro-F1 points, at a median 44 times lower measured cost. Its confidence is better calibrated than the verbalized confidence of 16 of the 19 LLMs, yet three frontier models show lower median calibration error (0.157 against 0.066). While items above 0.9 confidence are typically labeled accurately (median accuracy 0.815), on one task, empathy in peer-support dialogues, the model reports high confidence while performing near chance. Nonetheless, our results suggest that decision models are useful as a first step in the annotation pipeline: routing low-confidence items to an LLM matches or exceeds the LLM alone at a quarter to half of its cost.

Concepts are commonly defined as abstract, compact representations of knowledge and treated as basic units of intelligent behavior. Yet, cognition, psychology, and AI lack a shared mathematical language for them. Modern systems represent concepts as vectors, distributions, symbols, graphs, and other structures, but these formalisms are typically treated as competing rather than as solutions to a common problem. We propose an operation-based view that evaluates mathematical frameworks by the conceptual operations they support, identifying thirteen operations (including similarity, composition, generalization, and grounding) that recur across cognition, psychology, and AI. We show that ten frameworks embody distinct commitments to concepts as self-contained content, relational structure, or evolving process, and that these commitments determine which operations each supports naturally. For example, vector-based models facilitate graded similarity and generalization but struggle with explicit composition, whereas symbolic models support composition but offer but generalize poorly. No single framework we examined naturally supports all operations without extension. We test this account empirically using categorization as a case study, operationalizing nine theories on the same items against human judgments. Despite addressing the same conceptual question, the theories produce different procedures and results, demonstrating that mathematical commitment shapes what a theory can explain. We call for hybrid formalisms that treat content, relation, and process as jointly primary.

Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the protein annotation as a sequence-to-text generation problem. We fine-tune the 3B-parameter Ministral 3 base model with QLoRA (4-bit NF4 quantization with low-rank adapters) on sequence annotation pairs. We assess predictions with an LLM-as-expert protocol: a GPT model prompted as a senior molecular-biology curator scores organism identification as binary and function annotation quality. We conclude that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins. We also discuss future directions in data quality, model scaling, and evidence grounding that are needed to make the approach sufficiently reliable for practical use.

In recent years, large language models (LLMs) have emerged as a popular alternative for evaluation. Often referred to as LLMs as judges (LLJs), these systems have been widely adopted by researchers and practitioners across a broad range of measurement tasks, driven by their strong performance, scalability, and cost-effectiveness relative to human judgment. However, a growing body of work has shown that the use of LLJs raise concerns about their validity and reliability as evaluators. Existing efforts to address these challenges have largely focused on developing bias-mitigation techniques and refining prompting strategies. While these approaches represent an important step forward, they primarily offer technical fixes and leave a more fundamental challenge unaddressed: the lack of standardized, transparent, and reproducible evaluation practices. In this paper, we introduce LLJ Cards, a framework that synthesizes best practices from measurement theory, natural language generation, and machine learning literature into practical guidelines for LLJ-based evaluations. While LLJs offer a promising path toward scalable evaluation, their effective use requires grounding in rigorous evaluation principles to ensure validity, reliability, and reproducibility. LLJ Cards addresses this need by providing a structured framework for applying these principles in the design and reporting of automated evaluations.

Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the convergent, evidence-driven task of inferring a patient's condition from clinical data to produce a diagnosis, and clinical healthcare reasoning: the broader, navigational judgment required to communicate, plan, and adapt across multi-turn clinical interactions where a single correct answer may not exist. Recent benchmarks such as HealthBench and MedXpertQA reveal persistent weaknesses in both areas, exposing failures in complex diagnostic scenarios and limitations in contextual, patient-centered dialogue. We introduce a sequential training framework that targets these facets using synthetic data and rubric-based reinforcement learning. First, we improve diagnostic reasoning using MedBullets-derived questions with rule- and rubric-guided Reinforcement Learning (RL). We then shift to clinical reasoning by generating 5.3k synthetic multi-turn scenarios, each paired with multi-dimensional rubrics to comprehensively assess the response. This approach yields over 10% improvement on MedXpertQA, and our 30B model achieves 50.1% accuracy on HealthBench-Hard, surpassing proprietary baselines including GPT-5 (thinking). Our results show that targeted synthetic datasets and rubric-based training can systematically improve both diagnostic and interactive clinical reasoning in medical LLMs.

Sparse on-policy distillation (OPD) allocates teacher supervision to a small subset of tokens in student-generated trajectories. However, useful teacher guidance can yield a noisy update when its gradient is estimated from a sampled next token. We study this estimation problem at a fixed prefix in information geometry and propose an information-efficiency ratio (IER) based on a signal-to-noise decomposition. IER characterizes relative gradient estimation error under an optimal scalar baseline. A candidate-set approximation enables token selection based on IER and its combination with existing usefulness scores, while retaining the sampled reverse-KL training objective. On mathematical and medical reasoning tasks, adding IER improves existing selectors in multiple settings, with sparse configurations matching or exceeding full OPD without token selection at small token budgets of 0.1%–1%. These results support accounting for both usefulness and gradient-estimation reliability when allocating sparse supervision. Our code is available at https://github.com/BruceSheng1202/IER-OPD.

Speech-to-text engines are extremely needed nowadays for different applications, representing an essential enabler in human-robot interaction. Still, some languages suffer from the lack of labeled speech data, especially in the Arabic dialects or any low-resource languages. The need for a self-supervised training process and self-training using noisy training is proven to be one of the up-and-coming feasible solutions. This article proposes an end-to-end, transformers-based model with a framework for low-resource languages. In addition, the framework incorporates customized audio-to-text processing algorithms to achieve a highly efficient Jordanian Arabic dialect speech-to-text system. The proposed framework enables ingesting data from many sources, making the ground truth from external sources possible by speeding up the manual annotation process. The framework allows the training process using noisy student training and self-supervised learning to utilize the unlabeled data in both pre- and post-training stages and incorporate multiple types of data augmentation. The proposed self-training approach outperforms the fine-tuned Wav2Vec model by 5% in terms of word error rate reduction. The outcome of this work provides the research community with a Jordanian-spoken data set along with an end-to-end approach to deal with low-resource languages. This is done by utilizing the power of the pretraining, post-training, and injecting noisy labeled and augmented data with minimal human intervention. It enables the development of new applications in the field of Arabic language speech-to-text area like the question-answering systems and intelligent control systems, and it will add human-like perception and hearing sensors to intelligent robots.

In-context learning (ICL) based on large language models (LLMs) has shown promising potential in alleviating performance bottlenecks caused by the limited availability of annotated data in Named Entity Recognition (NER). However, existing methods still face issues of retrieval misalignment and generation uncertainty, making their performance heavily dependent on the LLM's capabilities. As the parameter scale of LLMs decreases, their performance in few-shot settings deteriorates significantly. In this paper, we propose a novel unified retrieval-augmented framework, URA-NER, including three key components: Progressive Granularity Retrieval (PGR), Model-aware Representation Enhancement (MaRE), and Reason-aware Knowledge Verification. PGR is a two-stage retrieval mechanism that achieves stage alignment. It first retrieves demonstrations for span detection based on the query's global semantics, and then for type classification based on the specific entity context, providing fine-grained local information. Moreover, MaRE employs entity pre-recognition to guide the construction of representations, ensuring the query and demonstrations are aligned within the LLM's semantic space and attention pattern. In addition, to mitigate generation uncertainty, we propose RaKV, a closed-loop "generation-retrieval-verification" process. It explicates the LLM's reasoning paths, leverages them for the retrieval of external knowledge, and reorganizes the knowledge into verification evidence aligned with the original reasoning paths. We conduct extensive experiments on multiple low-resource NER datasets. Results demonstrate that URA-NER significantly enhances the performance of LLMs under low-resource settings, with particularly pronounced gains for smaller LLMs, achieving new state-of-the-art results on several benchmarks.

Cross-domain Named Entity Recognition (CD-NER) aims to transfer the rich knowledge in the source domain to the target domain. Recent studies adopting decomposition or generation paradigms have achieved significant performance improvements, demonstrating high accuracy in entity span detection. However, during entity type classification, models severely suffer from entity type confusion, the erroneous tendency that models classify entities of one type in the text as another similar but incorrect type. To address this issue, we first propose a Multidimensional Confusion Quantification Model (MCQM) that quantifies a model's confusion extent between entity types from three dimensions: source-target hierarchy analysis, semantic similarity analysis, and explicit data evaluation. Moreover, we propose the Progressive Bidirectional Reasoning Chain (PBRC). PBRC leverages the source-target hierarchy and confusion analysis from the MCQM to prompt the LLM to generate two-stage reasoning information. The two-stage reasoning information is utilized to augment the knowledge of the model, significantly mitigating entity type confusion and improving the model's generalization performance. Experimental results demonstrate that our method achieves new state-of-the-art results on all domains of the CrossNER dataset.

Text-to-speech models for Bantu tonal languages are challenged by a tonal system that is rooted in both the lexis (i.e., the inventory of words, stems, and affixes) and the grammar (i.e., morpho-syntax). To complicate matters, the standard writing systems of these languages often omit tone markings and syllable duration information, which must be disambiguated by the reader based on context. Motivated by linguistic descriptions of Bantu language tone systems, we propose an end-to-end text-to-speech model that augments the text encoding mechanism with a morpho-syntactic prior. We replace the standard phoneme encoder in the VITS architecture with a morpheme sequence encoder and a phoneme-to-morpheme attention network. We posit that, by using this explicit morphological modeling, we can capture the information required to produce the correct tone. Experiments conducted on the Kinyarwanda language, a tonal and morphologically complex Bantu language, reveal substantial TTS improvement from this morphological modeling. Specifically, the proposed method significantly improves the naturalness, intonation, and intelligibility of the produced synthetic voices.

Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident than their corresponding pretrained language models (PLMs). Because task-specific labeled calibration data can be costly or unavailable, the corresponding PLM provides a natural label-free reference for post-hoc calibration. Prior agreement-gated PLM-referenced calibration fits a scalar temperature using only examples on which the PoLM and its PLM reference agree, excluding disagreement examples because direct alignment can drive the fitted temperature excessively high and induce under-confidence. We revisit this binary treatment. A controlled reintroduction diagnostic reveals a non monotonic aggregate effect: admitting a moderate fraction of disagreement examples can improve calibration, whereas the benefit diminishes as unit weight inclusion approaches the full disagreement set. We introduce SupportCal, a label-free post-hoc method that retains agreement examples at unit weight and assigns disagreement examples continuous weights based on the own-base PLM's relative support and corroboration from pretrained references selected from a size-compatible candidate pool. We further characterize when the resulting weighted objective admits a finite optimal temperature. Across MedMCQA and MathQA, SupportCal yields lower mean ECE than the agreement-only baseline for nearly all evaluated target-model configurations; supplementary TweetEval Sentiment results show the same pattern on a fixed-label classification task.

Text-to-speech (TTS) corpora are costly to record, yet many utterances add little new phonetic information. Core-set selection reduces this cost by choosing a small training subset under a fixed audio-duration budget. We represent a corpus as a phonotactic graph that links each utterance to its most phonemically similar ones, and we first test whether this graph has structure. In Bangla and English corpora, its clustering is 199 and 56 times that of a size-matched random graph, and its modularity is more than twice that of a degree-preserving random graph. We then propose Community Representative, a selector that samples across graph communities and spreads its choices within each one, starting from utterances rich in rare phonemes. At every budget and in both languages, it covers more rare phoneme bigrams than random and entropy-based selection, and this lead holds on held-out utterances. TTS models trained on its 20% core-sets have a significantly lower character error rate (CER) than models trained on equal-duration random or entropy-based subsets in both languages. When all models train for the same number of epochs, the Bangla core-set model also outperforms full-corpus training (3.93% vs. 4.47% CER) with 4.5x less training time.

Tool-use agent traces identify messages and API calls, but procedural analyses also need explicit units of action and inspectable links to their evidence. We present Canonical Procedural Actions (CPAs), an annotation protocol that records a procedural function, its first agent-event anchor, the agent events that realize it, and separate contextual evidence. Multiple actions may share a message anchor without an inferred within-message order. A retail case study produces a versioned 24-entry codebook through open induction, recorded consolidation, and successive application audits. Two isolated LLM contexts annotate 32 trajectories disjoint from development at the trajectory level, producing 499 and 491 occurrences with anchor-label overlap A=0.982. Requiring identical context-event references reduces overlap to 0.798. These are structural repeatability measures, not semantic accuracy: 16 of 26 task IDs also occur in development, and historical tool payloads were truncated to 110 characters. Retrospective controls show that collapsing all labels raises overlap to 0.986, while simple endpoint rules reproduce the tool-anchored portion with 0.997 overlap. Assistant-message actions have 0.971 overlap, with a per-label minimum of 0.816. Applying the frozen codebook to 244 further trajectories yields 4,058 records, including eight diagnostic outcomes. The contribution is an explicit, auditable annotation instrument and a case study of its construction and measurement limits; human-reference validity and downstream utility remain to be established.

Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astronomy and astrodynamics remains limited due to challenges in multi-step reasoning, symbolic manipulation, and domain-specific terminology. To address this, we present Taramandal-GPT (Constellation-GPT), a domain-adapted framework built on the Qwen3-8b backbone, enhanced with a Retrieval-Augmented Generation (RAG) pipeline and a fallback mechanism for improved contextual precision. We evaluate it on the Astrodynamics Problems Benchmark (APBench), a dataset of 299 questions covering foundational to advanced levels of space science. Using a dual evaluation method - numeric margin-based scoring and semantic similarity assessment - Taramandal-GPT achieves competitive performance against state-of-the-art open- and closed-source models, with notable strength in thinking-intensive tasks. These results highlight the value of specialized LLMs for domains demanding accuracy and interpretability, positioning Taramandal-GPT as a step toward reliable Artificial Intelligence (AI) assistants for astrophysics, spacecraft engineering, and space exploration.

We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contradictory in-context statements. We replicate their world-capitals experiments on 31 models spanning Pythia, GPT-2, Qwen3, and Ministral families, including base and post-trained variants, and extend evaluations to five additional knowledge relation types from the ParaConflict dataset. We empirically confirm most of their original findings: larger models and higher-frequency entities tend to favor memorized answers, with substantial family-level variance. However, several conclusions do not generalize cleanly: entity-frequency effects disappear on Qwen3-14B and 32B; post-training shifts the memory-context trade-off inconsistently across families; question phrasing alone can change a model's reliance on memorized knowledge by up to 80 percentage points; and semantically unrelated prose can mimic coherent supporting context. Our results clarify where Yu et al.'s claims hold and to what extent they generalize to other prompts.

Traditionally, the reliability of news publishers is assessed by expert organisations that evaluate editorial practices, transparency and factual standards at source. When this process is translated into a computational approach, the problem is often formulated at the level of individual articles, with models being trained on a set of pre-labelled articles and their performance being evaluated in a test phase. In this work, we investigate news source reliability inference as a source-level prediction problem. We propose a two-stage framework in which transformer-based language models first estimate the reliability of individual articles and subsequently aggregate article-level predictions to infer the reliability of previously unseen publishers. To approximate realistic deployment conditions, we enforce a strict publisher-disjoint evaluation protocol, ensuring that no publisher appears in both training and test sets. Experiments on 19,476 political news articles from 439 English-language publishers labeled with NewsGuard reliability ratings show that aggregation substantially improves robustness and performance, increasing accuracy from approximately 0.60 at the article level to 0.69 at the publisher level. Finally, we analyze how prediction errors vary across political orientations, revealing statistically significant associations between political leaning and misclassification patterns. Overall, our findings show that publisher reliability can be inferred from aggregated textual signals alone, supporting scalable and content-based approaches to automated news source assessment.

Evaluation benchmarks for Indian language automatic speech recognition (ASR) suffer from two systematic biases: optimistic scores from clean, controlled audio conditions, and pessimistic scores from overly rigid transcription standards that penalize valid linguistic variations. We introduce Vimarsha, a 100-hour benchmark spanning all 22 scheduled Indian languages, designed to address both distortions. Vimarsha combines demographically diverse on-field recordings with carefully mined in-the-wild audio selected for acoustic difficulty, alongside a lattice of variations framework that encodes multiple valid transcriptions per utterance. Evaluations of 10 state-of-the-art ASR models reveal substantial shifts in model rankings under realistic conditions, geographic and demographic performance disparities, and systematic failure modes across speaking rates and acoustic environments.

Looped Language Models (LoopLMs) perform "latent reasoning" by recursively refining internal latent representations with shared weights, offering a more effective alternative to explicit verbal reasoning. Despite their effectiveness, we find that LoopLMs remain prone to loop instability: unstable refinement across iterations can produce localized uncertain "hard" tokens associated with reasoning errors. To address this, we propose LoopCD, loop-wise contrastive decoding that enhances the reasoning performance of LoopLMs by intervening on these tokens at inference time. Specifically, we exploit the internal dynamics of LoopLMs and contrast the logits from earlier iterations with logits from the last refined iteration to form the final sampling distribution. We find that this strategy is highly efficient, introducing only negligible inference overhead and requiring no additional training, while effectively improving reasoning performance by naturally refining reasoning-critical hard tokens. Extensive experiments show that our method improves the performance of recent representative LoopLMs across various reasoning tasks.

Evaluation scores used around LLM systems – including reward models, rerankers, and LLM judges – can track surface form instead of the quality they claim to measure. When presented with a terse correct solution and a commented buggy solution for the same MBPP problem, a public preference reward model selects the correct one no better than a coin flip (0.507). Subtracting the predictable surface component from such scores is increasingly common, but removal alone does not yield a more valid measurement: the removed component may carry construct-relevant signal, and residualization cannot tell which is which. Under designed interventions – unit-test labels with comment-only edits – residualization attenuates the reward model's format effects by about 0.12 on both correct and buggy code, while the correct-versus-buggy margins move by less than 0.01. In observational NLI and QA settings, we freeze a held-out replication before scoring and re-evaluate it using labels from disjoint annotators; this supports only a narrower conclusion: better agreement with the construct labels on a pre-declared slice where a surface-only predictor errs, not a repaired score. Full-population agreement falls in every observational setting with a reported positive slice gain, and within-question ranking falls in every such QA setting. When construct and surface features are entangled, residualization can decorrelate a score while degrading construct alignment, and, in a controlled model, configurations just as damaging to construct alignment pass every pre-adjustment check, so no committed gate is a guarantee. We assemble these distinctions into a reporting protocol whose outcomes, refusal included, state what an adjusted score may be claimed to show: an audit-time diagnostic reported beside the construct-alignment cost it incurs, never a replacement for the raw score.

Legal information in Bangladesh is inaccessible to most citizens. Statutory text is English-only, trained lawyers are concentrated in urban centres, and cloud-dependent AI fails where mobile connectivity is unreliable, a setting in which hallucinated legal text causes direct harm. The system addresses statutory interpretation only; queries that require judicial precedent or case-law reasoning fall outside its scope. We target the statutory access gap by compressing a 9-billion-parameter Gemma-2 teacher into a 2-billion-parameter student through two-phase progressive knowledge distillation. Phase 1 performs supervised fine-tuning on 9,429 quality-gated legal question-answer pairs (65% acceptance from 14,514 generated queries); Phase 2 minimises sparse Kullback-Leibler divergence against the teacher's top-50 per-token logits at temperature tau = 4.0, implemented via QLoRA (4-bit NF4, rank-32 LoRA adapters). Prior legal language models target general legal English; this system specialises in Bangladeshi statutory law. Every response is grounded through hybrid retrieval combining dense semantic search (60%) and BM25 (40%) across 36,029 statutory passages from the Bangladesh Constitution and national legislation. On a 50-query English benchmark, the distilled model reaches ROUGE-L 0.4715 and BERTScore F1 0.5679, a 103% ROUGE-L and 143% BERTScore gain over the retrieval-augmented undistilled baseline (ROUGE-L 0.2323, BERTScore 0.2340). The adapter quantises to 1.6 GB (GGUF Q4_K_M) and runs at 4-8 tokens per second on a Pixel 6 with no network access. Cross-lingual evaluation on 50 Bangla queries yields ROUGE-L 0.4083 and BERTScore 0.8133, showing effective retrieval from Bangla input against an English-only corpus. In a single-evaluator pilot, a practising lawyer rated 50 responses at a weighted mean of 4.16/5 (90% rated 4 or 5), supporting utility beyond text-overlap metrics.

Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recent multimodal approaches attempt to incorporate textual signals, but they often treat text as static features or use large language models as forecasting backbones, limiting their ability to capture temporal dynamics and increasing computational cost. To address these challenges, we propose TAC-Time, a unified framework that transforms textual information into additional temporal channels. By modeling text features jointly with numerical sequences in a shared temporal backbone, TAC-Time preserves temporal continuity and periodic structures while remaining efficient and scalable. This formulation also enables systematic interpretability analyses. We show strong cross-modal dependencies through attention and frequency-domain analyses, and identify predictive textual signals whose correlation-aware alignment yields partial forecasting improvements. Extensive experiments on real-world multimodal benchmarks demonstrate that TAC-Time outperforms prior methods.

Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive processing. To address these challenges, we propose a new paradigm called the Data Agent, designed to manage, process, and analyze data with minimal human intervention. Data agents autonomously execute a wide range of data-related tasks, transforming traditional data systems by shifting from manual design to autonomous orchestration, from literal manipulation to semantic interpretation, and from reactive to proactive processing. Our Data Agent system includes six components: semantic data organization, semantic operators, agentic pipeline orchestration and optimization, feedback-driven refinement, memory management, and proactive adaptation. Building on this foundation, we also develop two specialized agents: the data analytics agent and the data science agent. Experiments on real benchmarks demonstrate significant performance gains of our data agent over state-of-the-art methods. We identify open challenges to guide future research in building fully autonomous data systems.

Retrieval-augmented generation (RAG) is hard to monitor in production: exhaustive relevance labels do not exist for non-stationary multi-million-passage corpora that re-index in real time. As a result, retrieval quality is generally understudied and often deprioritised in favour of generation-oriented metrics. In this work, we propose auditing retrieval coverage by probing for evidence of missing documents rather than enumerating every relevant one. Our method Re:CAP (REtrieval Coverage Audit by iterative Probing) is a reference-free audit loop applied to a deployed RAG pipeline's initial answer and retrieved context: it identifies the topics already covered, generates probing questions for plausibly missing topics, retrieves candidate documents, and applies an LLM-as-judge to retain only those that introduce previously-unretrieved information. On four public benchmarks, Re:CAP recovers 9-29% of gold labels that flat BM25 top-500 cannot reach, rising to 48% on TREC-COVID. On MuSiQue Re:CAP beats flat hybrid top-500 by +12.9 pp on recall at less than half the document budget. An ensemble BM25, dense, and hybrid baseline (top-500 each) still leaves out 21.2% of gold docs on TREC-COVID that Re:CAP recovers; human annotators judge that 78.9% of those structurally distinct documents add new information to the baseline answer (Fleiss $\kappa$ = 0.79, n = 123), and 73.9% on live production traffic (n = 180). End-to-end recall is reproducible to within $\pm$1% across three independent runs, making Re:CAP a stable instrument for periodic retrieval audits.

Questions scraped from the web are used across academia and industry as a proxy for what people want to know. Across QA training data, retrieval benchmarks, and content strategy, questions on a page are assumed to reflect human intent. We test this assumption at scale by extracting 13.4B question occurrences across 110 FineWeb snapshots (2013-2025), and report three findings. First, you can tell who is asking: provenance (the host/page of questions) leaves a signal in question form, and a logistic model can separate genuine user questions from templated/manufactured ones at AUC 0.725 via length and surrounding context rather than question type, though only 0.554 against commerce FAQ writing. Second, question frequency does not measure demand: the most-frequent questions are boilerplate/templated (over 70% of the top thousand), so occurrence counts measure how often a string was published and not how often it was asked. Third, over twelve years the genuine share of occurrences fell by 79% (42-56% after controlling for crawl composition), with question length and context decreasing. We present the first diachronic, occurrence-level measurement of web question provenance, and find the crawlable web's questions have shifted from being asked by humans toward manufactured for machines to read.

Generative AI enables scalable production of educational videos, but current systems largely focus on producing visually coherent content rather than supporting learning. As a result, generated videos often lack explicit pedagogical structure, reliable quality control, and mechanisms for assessing learner understanding or addressing misconceptions. In this work, we introduce PIVOT (Pedagogy-guided Instructional VideO Tutoring), a generative video tutoring framework for STEM learning via learning-centered instructional support.1 Inspired by conventional teaching workflows, our framework integrates pedagogy into the full generation pipeline: it first uses instructional principles to guide storyboard generation, then produces verified multimodal videos through code-centric generation and a pedagogical verification harness, and finally connects videos with assessment and misconception-aware remediation. Experiments and expert evaluations across four STEM domains show that our framework produces educational videos with pedagogically aligned content, clear and engaging presentation, coherent instructional flow, and perceived effectiveness for learning. These findings suggest a human-centered perspective on educational content generation: generative systems should be evaluated and designed not only by what they produce, but also by how they support teaching practices, learner understanding, and corrective feedback.

Best-of-$N$ is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and high-quality reasoning paths. However, post-trained reasoning models often suffer from exploration collapse, where independent rollouts repeatedly follow similar reasoning paths and limit the gains from increasing the rollout budget. Existing methods alleviate this issue by promoting broader exploration, but do not explicitly guide exploration toward continuations that make meaningful progress, resulting in limited exploration efficiency. To address this, we propose \emph{\underline{S}tate-conditioned \underline{P}rogress-guided \underline{S}teering} (SPS), a training-free latent steering framework. Specifically, SPS constructs a state-conditioned Direction Bank containing multiple progress-guided steering vectors for different prefix-state regions. During online inference, SPS retrieves a suitable steering vector based on the current prefix state and applies it at high-uncertainty transitions to guide the next reasoning step toward meaningful progress. Extensive experiments across multiple model scales and benchmarks demonstrate that SPS consistently outperforms strong baselines. Further analyses validate the effectiveness of its key designs and offer valuable insights for future research. The code is available at https://github.com/rattlesnakey/SPS.

Medical image interpretation is central to diagnosis and care, yet adapting general-purpose multimodal large language models (MLLMs) often requires resource-intensive domain-specific fine-tuning. Here we introduce representation-guided in-context learning (RG-ICL), a training-free inference framework that retrieves query-aligned demonstrations using frozen encoders, without task-specific parameter updates. Across eight datasets spanning histopathology, radiology and retinal fundoscopy, RG-ICL improved classification (mean gain 20 percentage points) and visual question answering (VQA) (mean gain 13 percentage points) over no-context and conventional ICL, approaching or exceeding training-based comparators. Which cases were retrieved mattered more than how many: 6 query-aligned cases outperformed up to 32 randomly selected ones, whereas fixed or random cases often reduced accuracy below baseline. For VQA, aligning reference cases with both image content and question intent produced further gains. These findings indicate that for medical image interpretation, curating which reference cases an MLLM sees is a practical alternative to retraining it.

Crash datasets that carry an investigator narrative hold information the coded fields omit. Coding those narratives at scale has been blocked by three obstacles. Frontier large language models are costly at that scale, their generated text cannot be verified, and no rule says how much output a human must check. This paper formulates narrative coding as gated, typed decisions answered by Jev, a System One model that returns probabilities over analyst-defined options and generates no text. A screen covered 499,500 Texas narratives and 195,857 were coded with a 27-question schema. Cost is governed by schema size rather than narrative length. The probabilities are audited against coded fields and against 2,416 blinded human judgments drawn under a stated sampling design. Two frontier large language models are benchmarked on the same records. Against human labels the typed model attains an F1 of 0.908. One frontier model gains 0.059 and the other is indistinguishable from it. Calibration varies by model rather than by paradigm, so each model must be audited. Recalibration on the same labels reduces calibration error by a factor of 3.3. Agreement with coded fields understates fidelity to the narrative by a median of 0.26 in kappa. A resolution-floor bound covers any model that reports probabilities on a discrete grid. A review budget over flagged records gives the records a human must read per variable and per year. Adding the calibrated variables to the coded fields raises the injury and fatal crashes attributed to nine factors by 10,747 per year.

Generating coherent meta-reviews from multiple peer reviews is challenging when reviewer evidence conflicts and varies in reliability. Existing approaches typically formulate meta-review generation as a multi-document summarization task and aggregate reviewer feedback uniformly, making it difficult to determine which opinions should be prioritized under disagreement. In this paper, we study meta-review generation through reliability-aware evidence aggregation. Our framework first extracts aspect-level opinions from peer reviews and identifies conflicting evidence within each aspect. It then estimates opinion-level support and review-level quality to measure evidence reliability. Based on these signals, the framework assigns reliability-aware weights to reviewer feedback, enabling the generator to prioritize better-supported arguments while preserving diverse perspectives. Experiments demonstrate that our method consistently improves meta-review generation over strong baselines on both automatic and human evaluations, with clear gains in conflict recognition and resolution under high-conflict review scenarios. The code and implementation details are publicly available at https://github.com/Wangxz729/reliability-aware-meta-review.