Papers

In numerical signal processing for electroacoustic composition, the progressive loss of specific development and research environments caused by the increasing use of digital market tools has favoured the dominance of the closed-architecture audio processor model. This model, while powerful, envisions the possibility of describing output data about its perceived characteristics, but at the cost of ignoring its internal process and interacting systems, which become complex, powerful environments but closed in an inscrutable black box, a loss we must consider. Any digital signal processing technique tells a story. Just as the words of a language incorporate social, historical and technical polysemic layers, a signal processor has its own story of implementation, a gradual technological achievement with its inevitable aesthetic consequences. Through the looking-glass of literature, one can access those environments with renewed awareness by reestablishing a scientific method and an attitude to research. In this specific case, starting from the case study of Manfred Schroeder's historical reverbs, we illustrate the process of building analytical evaluation tools, as well as practical implementation, at the basis of a conscious study path.

Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM, FEniCS, or COMSOL takes real expertise. Large language model (LLM) agents promise to turn a natural-language request into a working simulation, and recent CAE agents add simulation-specific machinery: multi-agent decomposition, domain retrieval, and scripted reflection. That machinery suited weak base models; modern harnesses already supply multi-turn reasoning, tool use, and execution feedback. We ask what a CAE simulation agent still needs beyond a generic harness. With information access and repair budget held fixed, a single-agent harness matches or beats multi-agent specialized systems (FoamBench 96.4% vs.\ 88.2%). Ablations trace this to capabilities the harness already provides: execution-feedback repair lifts FoamBench from 71.8% with no repair round to 96.4%, while scripted reflection adds nothing. The one input that still helps is domain knowledge supplied as solver tutorials, our largest measured gain (80.9% to 96.4%).

Coreference resolution is an important task in contextual reasoning. In this paper, we investigate the mechanism for representing and retrieving singular and plural entities for plural reference. We use a combination of mechanistic interpretability and attention pattern analysis to study the process in which LLMs predict a pronoun to refer back to previously mentioned entities. Using a range of causal intervention techniques, we find a set of attention heads that are responsible for (1) representing coreference information in the input, (2) identifying entities that form a plural reference, (3) transferring the information to the component that is responsible for selecting the antecedents and predicting the pronoun. We also find that LLMs align with humans in preference for plural pronoun. Specifically, entities in a plural construction are more likely to be referred to as a plural entity if they are ontologically similar and are linked by the conjunction "and".

Understanding the composition of large-scale autonomous driving datasets is essential for safety, robustness, and reliable operation across domains. For example, domain shift between locations could lead to the operating environment being misaligned with the training data, resulting in potentially dangerous performance degradation. Yet, existing data analysis pipelines largely rely on metadata, predefined labels, or manual inspection, which provide limited semantic insight or do not scale. This paper studies set difference captioning: given two subsets of images, the goal is to produce a natural-language hypothesis describing differences between the target and reference set. Building on a two-stage formulation, we adapt the method to autonomous driving by focusing on object-centric patches derived from object detection, which simplifies aggregation and enables attribution of differences to specific object instances or categories. To evaluate this setting in-domain, we introduce a new benchmark, AD-Diff Bench. Low-concentration experiments assess the suitability of set-difference-captioning approaches to sparse, real-world differences. We restrict our experiments to open-weight models to support reproducibility and ease of deployment. The proposed benchmark and analysis provide a step towards practical, human-interpretable dataset introspection for autonomous driving datasets. Our implementation and benchmark dataset are available at https://github.com/KIT-MRT/AD-Diff

The comparative analysis of banks' financial statements poses significant challenges for automated question answering systems due to their complexity, substantial length, technical language, and inhomogeneity of both textual and numerical content across different jurisdictions and institutions. We introduce FinRAG-QA, a novel benchmark dataset for financial question answering, which comprises 999 practitioner-curated questions on 10 standardised indicators, grounded in 209 annual and Pillar 3 reports from 24 major European and U.S. banks spanning 2019-2023. Unlike prior financial QA benchmarks, which centre on U.S. filings and single-institution analysis, FinRAG-QA targets cross-institutional retrieval over documents averaging 198k words, longer than any existing financial QA resource. On this benchmark we evaluate a multi-stage RAG pipeline and isolate the contribution of each component. Contextual chunk enrichment combined with a retrieval-optimised embedding model raises NDCG@10 from 0.322 to 0.710; conditional on the ground truth being retrieved, a reasoning-optimised generator raises answer accuracy from 44.6% to 79.0% (+34.4 percentage points), at roughly 20x the generation latency. We further show that cross-encoder reranking degrades retrieval when the first-stage ranking is already strong, and that a single top-ranked chunk outperforms larger contexts at generation time. Experiments were run in late 2024-early 2025 with the models available at that time.

Synthetic data augmentation has become a common strategy for addressing class imbalance in NLP, but most approaches focus on the quantity and diversity of generated examples rather than their geometric relationship to real training data. We investigate this question in the context of discourse pragmatic function classification, a task where data sparsity is a structural feature rather than a collection artefact. Using 410 manually annotated instances of the English word look drawn from the British National Corpus, spanning four functions: Attention Signal, Directive, Discourse Marker, and Interjection. We generate synthetic training examples with Llama 3.1 and partition them by their cosine distance from real training data in RoBERTa embedding space. We compare six training conditions that differ in the placement of synthetic examples relative to the empirical decision boundary, while holding augmentation quantity constant across conditions. All augmented conditions improve macro F and accuracy over the real only baseline, but core proximal examples (NEAR) yield the largest gains in macro F (0.113), while a distance balanced mix achieves the highest accuracy (0.748). No condition improves AUC, indicating that augmentation shifts the decision boundary rather than improving the model's underlying probability estimates. These findings suggest that where synthetic examples land in representation space matters as much as how many are generated, with implications for low resource pragmatic classification more broadly.

Chain-of-thought (CoT) reasoning improves large reasoning models (LRMs) on complex tasks but often produces long, redundant traces. Recent training-free early-exit methods shorten these traces by choosing an intermediate point to stop reasoning. We study one such strategy that injects an end-of-think token (EoT, </think>) at this point to trigger the reasoning-to-answering transition, and find that the injected EoT does not always induce a clean answering phase. Answering-phase generation can continue before the model regenerates another EoT, with the span preceding this regenerated EoT scaling with the reasoning tokens saved by early exit and exhibiting continued reasoning behavior. We call this spurious CoT termination, where reasoning-like generation continues into the answering phase. We hypothesize that insufficient attention to the injected EoT contributes to spurious CoT termination and probe this hypothesis with Exit-token Attention Biasing (EAB). Across four LRMs, five benchmarks, and two early-exit methods, increasing attention to the injected EoT reduces spurious CoT termination and answering-phase length. These results reveal a limitation of controlling LRMs by externally matching their explicit think-block format. Inserting the EoT token conforms to this format but does not by itself guarantee the intended reasoning-to-answering transition. Our code is available at https://github.com/Seunghee-Koh/Spurious-CoT-Termination.

Multi-agent debate (MAD) improves the reasoning capabilities of large language models by having multiple agents iteratively refine their responses through discussion. However, MAD suffers from a critical vulnerability known as shared misconception: when a majority of agents initially converge on an incorrect answer, the debate process tends to amplify rather than correct the error. Existing methods primarily address peer skew but leave the agents' inherently biased concept priors unaddressed. To mitigate this systematic weakness, we propose R$^2$-MAD (Remember and Reweight for Multi-Agent Debate), a framework that equips agents with an experience memory accumulated from past debates. R$^2$-MAD intervenes on both failure modes through two complementary mechanisms: A debate-state-aware retrieval policy dynamically calibrates the concept prior by retrieving relevant historical evidence based on the current consensus level. Then these retrieved experiences provide a basis for estimating per-agent reliability, yielding confidence weights to modulate peer influence. Experiments on various benchmarks show that R$^2$-MAD achieves consistent improvements over existing single-agent and MAD baselines.

Land ownership in Bangladesh is recorded in Ana-Ganda-Kora-Kranti-Til, a base-16 positional fraction system with dedicated Unicode glyphs, no mainstream font, and no coverage in any OCR pipeline or tokenizer. The handwritten records that carry these fractions, RS Khatians, are the authoritative title record for millions of parcels and a frequent subject of civil litigation, yet no benchmark has asked whether a machine can read one. We introduce KhatianDoc, a four-task benchmark built from 107 real RS Khatian records from the Vumi (land) Office of Munshiganj, Bangladesh: symbol recognition, base-16-to-decimal conversion, structured field extraction, and legal document question answering over 1,634 QA pairs. Ground truth was transcribed by hand, verified by a land-law practitioner to full agreement, and anonymized through positional tokens that keep the referential distinctions multi-hop questions depend on. We evaluate six multimodal LLMs (8B to 72B+, open and closed) under a fixed zero-shot protocol. Five QA categories, 39.3% of our stratified set, return zero correct answers from every model; on the arithmetic task, every model that emits a number does worse than a constant-mean baseline, with exact- and near-match scores coinciding: decorrelation, not approximation. Auditing our own metrics surfaced two artifacts in opposite directions: we correct a refusal-scoring bug and report the fixed scores beside the originals, and flag an inflated metadata metric as an upper bound. KhatianDoc documents not a performance gap but the absence of a capability, with verified ground truth for future systems. Code and data, with a redacted image release, are publicly available.

We investigate what makes synthetic OCR supervision transfer to real Thai documents and use the resulting insights to build Wayu-Paxa-OCR-Zero, a Thai OCR model adapted without OCR labels from real Thai document pages. Synthetic data provide exact labels at scale, but "realism" conflates source domain, page context, typography, spatial structure, and glyph variation. We disentangle these factors with a controlled document-reconstruction pipeline and evaluate each variant under page- and crop-level training on printed and handwritten Thai documents. Non-text context has little consistent effect, whereas typeface diversity, two-dimensional structure, and real handwriting glyphs improve transfer; moreover, source-domain matching depends on training granularity, with in-domain reconstruction approaching real printed supervision under page-level training (1.82% versus 1.31% median character error rate) but underperforming out-of-domain reconstruction under crop-level training (15.59% versus 5.52%). Guided by these findings, we adapt the 0.9B-parameter PaddleOCR-VL-1.6 into Wayu-Paxa-OCR-Zero using 45,723 synthetic pages: relative to its base checkpoint, it reduces median character error rate from 6.64% to 1.24% on printed pages and from 74.87% to 20.55% on handwriting and outperforms Typhoon OCR v1 7B on all five evaluation sets, showing that synthetic-only training can be competitive.

The growing scale of academic peer review has motivated the use of Large Language Models (LLMs) as review assistants, yet LLMs can generate fluent but unsupported claims that undermine review reliability. Existing hallucination benchmarks are not designed for peer review, where verification requires grounding claims in long, technical papers. We introduce HalluPeer, a benchmark for detecting hallucinations in scientific peer reviews, providing aligned triples of paper content, human-written reviews, and hallucination-injected reviews, annotated for detection, classification, and localization. Our pipeline induces a peer-review-specific hallucination taxonomy, identifies review contexts, and injects hallucinations with automated filtering. Experiments on 12K papers and 38K reviews show that existing detectors struggle to separate hallucinations from legitimate critique, while evaluation on authentic reviews demonstrates that HalluPeer-defined hallucination patterns occur in real peer reviews, highlighting the critical need for source-aware verification. Our project page can be found in https://github.com/Lin-TzuLing/HalluPeer.git

Language models are commonly discussed as technical artefacts, but they are obviously shaped by the linguistic worlds conveyed by data during their training. Using Italian language models as evidence, I want to bring attention to the nature of the systems which result from training and specialising models on translated and synthetic data, and further curating them, and to the meaning of testing them on equally unnatural data. Are these eventually models of Italian? Are they models of language? Does NLP still care about language? These questions yield another, more concrete question: what language do we actually want language models to produce? I argue that this question cannot be answered if we do not first consider a clearer distinction between language models designed as technical products and language models designed as tools for studying language itself. The answers then might be diverse, the languages we are talking about might be diverse, and the picture might not be as pessimistic as we fear.

Large Language Models (LLMs) demonstrate strong multilingual reasoning performance, yet their robustness to semantics-preserving structural variation remains underexplored, particularly for relatively free word-order languages. We investigate the structural sensitivity of multilingual LLMs using two linguistically grounded perturbation settings in Hindi and Malayalam: constrained constituent reordering and active-passive voice transformation. We introduce a benchmark dataset IndicReStruct, with two variants, GSM8K-Reordered and GSM8K-Voice, constructed from GSM8K while preserving semantic meaning. Across six state-of-the-art LLMs and multiple prompting strategies, we observe consistent and significant degradation in mathematical reasoning performance under structurally perturbed inputs. To further understand these failures, we perform qualitative error analysis and mechanistic interpretability experiments using residual-stream activation patching. Our analyses show that reasoning failures frequently arise from disruptions in entity-quantity alignment and that intermediate transformer layers contribute most strongly toward reasoning restoration. Overall, our findings suggest that current multilingual LLMs remain highly sensitive to surface syntactic realization and lack robust compositional invariance under structurally different but semantically equivalent inputs.

In low-resource settings, deploying TTS typically requires choosing between a large voice-cloning model with costly inference or a compact fixed-voice system that requires a speaker-specific corpus. We study a third route: using a large voice-cloning model as a programmable data source to turn a short voice reference (e.g., 15 seconds) into a compact fixed-voice student trained entirely on synthetic speech. This setting makes pipeline design consequential: teacher errors become training targets, while filtering failed generations can reduce coverage of difficult texts. Thai further introduces challenges from ambiguous word boundaries, lexical tone, names and loanwords, numeric verbalization, and Thai-English code-switching. We study how text preparation, synthetic generation, quality filtering, rejection sampling, and frontend choices affect the resulting student, and where teacher limitations remain. We evaluate CER, Challenge-Set Keyword Accuracy, Prosody Pause Accuracy, speaker similarity, and speaking rate. The resulting 82M-parameter model, Wayu-Paxa-TTS-Edge, enables on-device Thai TTS without reference audio. It achieves 68.2% Challenge-Set Keyword Accuracy (85.5% of Gemini 3.1) and 91.4% pause precision, outperforming its OmniVoice teacher (89.9%) and reaching 94.8% of Gemini 3.1. It also achieves the lowest pause-placement error and intra-word pause rates among the three systems, and 3.7% and 1.1% CER on Thai and English, respectively. We open-source the model and evaluation framework for Thai TTS development.

Knowledge graph embedding (KGE) demonstrates its effectiveness for predicting missing links in knowledge graphs (KGs) by projecting entities and relations into a low-dimensional vector space. It is crucial for KGE models to effectively capture inference patterns (patterns) inherent in KGs, such as symmetry/antisymmetry, inversion and composition. Although recent KGE models exhibit strong capabilities in modeling such diverse patterns, they suffer from inherent limitations stemming from pattern over-generalization, where embeddings learned from only a single pattern instance inevitably generalize that pattern to all related instances, i.e., generalize the pattern universally. To address this issue, we propose PogRE (Pattern Over-Generalization Robust Embedding), a simple but effective method that utilizes dense linear transformations and compound operations for relation representation. Our theoretical analysis demonstrates that a dense linear transformation allows a pattern to become progressively universal as more triples are observed in the pattern. Furthermore, after observing d+1 linearly independent entities (d+1 denotes the dimension of entity), the linear transformation guarantees universal generalization of the pattern across all related instances. Experimental results on three standard benchmark datasets show that PogRE outperforms existing state-of-the-art KGE models in link prediction. Moreover, our empirical results indicate that PogRE effectively addresses the negative impact of over-generalization.

Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. However, existing benchmarks primarily evaluate memory through QA-style probing rather than in-situ conversational usage. We introduce LOCOMO-CONV, a conversa- tional memory benchmark derived from Lo- CoMo with four query styles: dialog, implicit, counterfactual, and composed. Across five rep- resentative memory systems, we evaluate both retrieval recall and end-to-end response qual- ity. Our experiments show that conversational framing exposes substantial retrieval gaps over- looked by QA benchmarks, especially on im- plicit and composed queries, which multi-facet query rewriting narrows for raw-turn mem- ory but not abstractive memory. We further find that strong retrieval does not fully trans- late into response quality, and that implicit queries exhibit silent grounding, where mem- ory improves contextual grounding without ex- plicitly surfacing the gold fact. These results point to reasoning-based memory elaboration as a promising direction, and we release aux- iliary supportive_memory annotations captur- ing conversationally useful context beyond the original gold evidence.

Retrieval-augmented generation (RAG) can improve the specificity and grounding of large language model responses, but its effect is not uniformly beneficial in single-turn mental-health question answering, where user queries often combine emotional distress, treatment concerns, and safety-sensitive needs. We study when retrieval helps or hurts mental-health QA, and whether a lightweight selective retrieval policy can better control this trade-off. We operationalize retrieval need using three draft-conditioned utility dimensions: psychoeducational need, coping need, and response specificity, together with a rule-based safety trigger. Following psychotherapy-grounded RAG systems such as coTherapist, we construct a compact and controllable guideline corpus comprising coping-strategy, psychoeducational, and safety resources. We fine-tune an instruction-tuned generator on MentalChat16K using QLoRA and compare Closed-book, Always Retrieval, and Selective Retrieval settings on CounselBench-Eval and CounselBench-Adv. Experiments show that retrieval is not uniformly beneficial in this domain. Always Retrieval improves specificity but lowers overall quality and introduces additional safety-sensitive failures. Selective Retrieval preserves closed-book behavior for low-need cases while avoiding the additional degradation caused by unconditional retrieval, supporting the view that retrieval activation is a safety-sensitive control decision.

A model that inherits one-line memories may pull one archived source record before acting; a directive in the store can steer that pull: a pointer, a criterion or both. Across sixteen registered studies (179,352 attempts) we measured where the request goes under each form; every result is descriptive, with registered intervals, no mechanism claim. A length-matched criterion exceeded a bare id on six direct-provider models (D) and failed its registered superiority rule on a nine-model OpenRouter panel (E). On generated worlds (K2-K5): the two registered signatures held on Opus 5 and Fable 5.1, Fable 5 followed the same sign, Haiku 4.5 reversed, and Sonnet 5, the GPT-5.6 endpoints and GPT-6 Astra lay near zero (K2). With a defensive adapter at five gains, the 70B rule for a gain-dependent change of the composite - criterion contrast was not met (K3 and K4); under the 8B attenuation rule (0.95 intervals: slope below zero; change beyond the margin), the 8B change of -17.5 [-26.7, -8.1] did not meet it on 36 families (K4) and at registered power on 337 families -16.6 [-19.4, -13.8] did (realised one-sided error at the margin 1.8 to 3.2% per corner of a finite grid, nominal 2.5%, not a uniform-error guarantee; K4's status stands; K5, first ladder), while a second SecAlign++ adapter under the imposed Meta-SecAlign template did not (-11.8 [-14.3, -9.3]; K5, second ladder); no NOT-MET is a statement that the contrast was unchanged; their difference (+4.7 [+2.3, +7.2]) describes two fixed execution paths, licenses no superiority, equivalence or 'significant difference' claim; nothing follows from the statuses differing (K5). Intervals describe family-reweighting stability conditional on the execution, not reproducibility across engine executions; audit replays were neither substituted for nor averaged into outcomes; no missingness gate fired and directional completions changed no status.

Reasoning traces of large language models are widely read as containing "breakthrough" moments and early-legible fates. Both readings rest on measurements missing a counterfactual control at the level of the claim; we supply both controls. First, a restart-controlled truncation probe separates when a solution fits the continuation budget from when a prefix carries value that fresh computation cannot buy, comparing per-anchor continuation solve rates against from-scratch restart curves at matched total generated-token budget. Applied to 178 problem-model cells (89 MATH problems x two small open models, an outcome-blind but difficulty-targeted cohort), exactly 1 of 178 cells survives as prefix-limited; restart dose-response separates a compute-starved model from a capability-limited one; and wherever the matched budget lies inside the restart grid, continuing the model's own prefix beats restarting (9 of 9) – predominantly compute compression rather than expanded reachability. Second, a pre-registered, difficulty-controlled test finds no detectable outcome information in early-window internal signals beyond a problem-difficulty baseline, and two generation-free analyses of public corpora show why this control is needed: a trace-blind difficulty proxy reaches AUROC 0.873 on 192K DeepSeek-R1 generations – inside the published probe range – and a closely matched reconstruction of the closest published early-window positive recovers a comparable pooled result (0.849) while within problem it is statistically indistinguishable from chance at all ten anchors (0.496 at t=4); a post-hoc within-targeted probe finds only a small average residual, concentrated in three low-failure problems. High pooled probe AUROCs cannot by themselves establish within-attempt information; a question-only baseline or within-problem evaluation is required.

Automated evaluation of creativity tasks remains challenging for LLM-as-a-Judge, as LLM is susceptible to biases such as verbosity bias and leniency bias. Such limitations are particularly evident in Contextually-Grounded and Procedurally-Structured Tasks (CGPST), a complex multi-step creativity task where inter-step dependencies, highly subjectivity, and wide scoring ranges lead to more unstable and biased judgments. Existing approaches either rely on task-specific training or directly apply LLM-as-a-Judge, both of which struggle to ensure reliable evaluation under such complexity. To bridge these gaps, we propose CreaEval, an automated creativity evaluator for CGPST that decouples typical LLM-as-a-Judge into analysis and judging. Correspondingly, CreaEval involves two critical phases: Memory-augmented Analysis, a SoT-LLM converts multi-step responses into structured evaluation evidence, incorporating cross-step memory; and Evidence-based Judging, a Judge-LLM uses the extracted evidence for judging without accessing raw responses. Comprehensive experiments show that CreaEval achieves an average performance improvement of 22.74% over the second-best baselines across CGPST and two classic simple creativity tasks, demonstrating its generalizability. The code is available at https://github.com/Jaong/CreaEval.

Large language models achieve superior performance on tasks that require extended reasoning, but long chains of thought make the KV cache a severe memory bottleneck. Existing KV cache compression methods share one paradigm: score each cached token by some estimate of how much it will matter later, and keep the top-scoring ones. We show that the selection signal contributes almost nothing. Random Attention keeps the prompt and evicts uniformly at random within each attention head, computing no score at all; across four models and six reasoning tasks, it matches the strongest baseline in task performance while delivering 32-43% higher throughput than that method when deployed with vLLM. Controlled experiments explain this by showing that 1) the prompt is the fragile part of the cache, and most of the gap between selectors is just whether their selection signal happened to keep it; 2) the reasoning trace protects itself against eviction with redundancy at two levels, in the text (the model restates what it still needs as it works) and across attention heads (each keeps its own copy of the trace), so once the prompt is safe, a random draw retains enough copies of what the model still needs, and no score is required to pick them. Our code is publicly available at https://github.com/SalesforceAIResearch/Random-Attention.

Transformers lack a native lookup mechanism, requiring repeated dense computation to recognize and reuse local static patterns. Lngram v1 introduces tokenizer-independent conditional memory through discrete latent n-gram addressing, but its memory capacity is coupled with the backbone width, limiting scalability due to high parameter and activation costs. We propose Lngram v2, which decouples the number of routes, memory dimension, and backbone width, and introduces a context-aware grouped-query attention readout to scale memory capacity independently. A zero-value Sink and counterfactual surrogate gradients further improve readout selectivity and routing trainability while preserving hard discrete addressing. Experiments across vision–language models (VLMs) of different scales show consistent improvements, including successful scaling to a 30B-parameter model. Compared with Lngram v1, Lngram v2 substantially reduces both total and activated memory parameters while maintaining or improving language modeling performance. Further analysis shows that its discrete IDs preserve substantial semantic structure of continuous hidden states, enabling semantic recovery from IDs alone and stable ID–semantic associations across datasets. These results establish Lngram v2 as an efficient and scalable latent conditional memory mechanism whose discrete addresses also provide a structured interface for analyzing internal model representations.

Idiomatic expressions are an integral part of natural language, reflecting cultural nuances and posing unique challenges for computational models, particularly in low-resource languages. In this paper, we present the first large-scale benchmark dataset of Bangla idioms, complemented by a synthetic multiple-choice question (MCQ) dataset for idiom meaning identification. We conduct a comprehensive evaluation of recent large language models (LLMs) across three idiom-related tasks: paraphrasing, idiom span detection, and meaning identification, leveraging zero-shot and few-shot prompting strategies. Our results reveal substantial variability in model performance, with no single LLM consistently outperforming others across all tasks. Notably, Phi-4-mini-instruct excels in paraphrasing, Kimi-K2-32b-instruct in span detection, and Gemini-2.5-flash in meaning identification. We believe that our datasets and analyses will provide valuable resources to guide future research in improving LLM comprehension of idiomatic expressions, particularly in Bangla and other low-resource languages.

Large Language Models (LLMs) have shown strong performance on table question answering, yet their accuracy often degrades as table size increases. We find that this degradation is not uniform across question types. Localization-sensitive questions are particularly affected by irrelevant table content, while questions requiring broader evidence may still benefit from full-table reasoning. Based on this observation, we propose a question-adaptive framework that dynamically selects between localized and full-table reasoning. The framework constructs question-specific sub-tables through operation-aware table decomposition and uses the predicted question type to determine the appropriate reasoning mode. We further introduce silver reference sub-tables for evaluating evidence selection and construct SLQA, a benchmark based on real-world long tables. Experiments on WikiTQ and SLQA show that localization is particularly effective for lookup and local reasoning questions, while adaptive selection between localized and full-table reasoning achieves the best overall performance. These results highlight that long-table QA requires deciding not only how to localize, but also when to localize. Our code and datasets will be made available upon publication of the paper.

Emotion recognition benchmarks often predict one emotion per text, missing many real-world scenarios where two people arrive at opposing emotions from a single shared event. For example, a child kicks the seat in front of her in excitement while the passenger ahead grows angry. We introduce CHIARO, a 1,000 human-annotated sentence benchmark for contrastive emotion inference grounded in appraisal theory. Each scene describes one causal trigger eliciting a positive emotion in one person and a negative emotion in the other, drawn from a ten-class taxonomy. We benchmark seven frontier LLMs and four off-the-shelf emotion classifiers. The strongest LLM reaches 67.3 macro-F1, well below human agreement, while existing emotion classifiers score near chance. Beyond evaluation, CHIARO also serves as a training signal. When combined with an existing emotion corpus, the resulting downstream classifier improves on CHIARO itself and on six of ten external emotion benchmarks, which positions our dataset as a complementary signal for emotion recognition.

In frame semantics, sentence comprehension is assumed to proceed by relating lexical meaning to background knowledge called semantic frames, thereby enabling readers to implicitly enrich the text with unstated information. Recent large language models (LLMs) have achieved strong performance across a wide range of downstream tasks. However, it remains unclear whether they can reproduce the kinds of implicit enrichment that humans naturally make during comprehension. To address this question, we introduce FrameBench, a benchmark grounded in frame semantics. FrameBench consists of multiple-choice questions that test whether models distinguish the frames evoked by the same verb across contexts. We construct the benchmark for English and Japanese using FrameNet-style resources and a generation-and-verification pipeline with native-speaker judgments. Our experiments on a diverse set of models reveal challenges for small models, while several large models surpass the human reference scores. We release the constructed FrameBench dataset and the code for dataset construction and evaluation at https://github.com/SasanoLab/FrameBench.

Accountability means a decision can be examined, justified, and contested. LLMs make this hard: fluent output may be ungrounded, incomplete, or unfaithful to the decision process. Achieving accountability requires verified rationales (how was the decision reached), assumptions (what was assumed rather than known), policy consistency (the same treatment for the same facts), and pivotal conditions (what would change the outcome). We introduce self-faithfulness as an automatic test of accountability: changing the pivotal conditions should change the decision. We examine accountable AI through clinical trial matching, a high-stakes task central to evidence-based medicine. Although LLM-based matchers match patients to trials reasonably accurately, they apply decision policies inconsistently and produce rationales that are unfaithful to their own decisions. We introduce VERDICT, an LLM-based agent that translates a decision task, its constraints, and its policy into Satisfiability Modulo Theories (SMT), then derives the decision with SMT and MaxSMT solvers – so policies are applied consistently and decisions are accountable by construction. Across a SIGIR 2016-derived dataset and TREC 2021, VERDICT achieves the strongest decision accuracy among LLM-only and neurosymbolic baselines, applies policies with perfect consistency, and produces clinician-preferred rationales grounded in explicit assumptions and pivotal conditions, with improved counterfactual self-faithfulness.

Logit-based knowledge distillation for autoregressive language models usually aligns teacher and student next-token distributions over the entire vocabulary. However, this global objective overlooks relative preferences among likely token alternatives. Existing local approaches often select candidate tokens from either the teacher or the student alone. Teacher-only selection can miss tokens that the student considers likely, while student-only selection can rely on an inaccurate ranking early in training. We propose Adaptive Local Relational Alignment (ALRA), a position-specific framework combining student proposals with teacher guidance. At each valid prediction position, the student proposes likely tokens, while the teacher's most probable token is included as an anchor. ALRA adjusts the number of selected tokens according to how broadly the teacher distributes probability within this candidate set relative to the current batch. Adaptive Local Divergence retains the mass-matching term and separately matches the relative token distributions within the selected and remaining vocabulary regions. Unlike the exact full-vocabulary decomposition, it replaces the teacher-mass coefficients of the two conditional terms with unit coefficients, preventing either term from being downweighted solely because its region has low teacher probability. Student-Weighted Pairwise Relational Alignment emphasizes high-probability token pairs with small student probability gaps and gives less weight to unlikely or clearly separated pairs. Experiments on The Pile with randomly initialized 200M- and 500M-parameter students across nine zero-shot benchmarks yield average accuracies of 36.62% and 37.40%. ALRA exceeds the strongest competing distillation baseline by 0.94 and 0.83 percentage points and improves over pre-training without distillation by 2.31 and 2.91 points, respectively.

Pretraining data for Armenian, a morphologically rich and low-resource language, is scarce, and no open Armenian LLM has been released with the data and recipe needed to reproduce it. To address this gap, we curate and release two datasets. ArmWeb is an extensively validated corpus of 4.37M Armenian news documents. ArmSTEM is a parallel English-Armenian collection of 373K math and science problems with step-by-step solutions, translated into Armenian and verified through both answer-preserving LLM judgment and human evaluation. Continued pretraining of Gemma-4-E4B on these datasets yields arm-gemma-e4b, which outperforms every existing open Armenian model as well as its unadapted base, and is the first open Armenian LLM with complete training data and recipe. Our ablations show that news-only continued pretraining improves fluency while eroding knowledge, a pattern we also observe in existing Armenian models, and that a small share of verified translated STEM data reverses the loss. We further find that the largest public Armenian corpora overlap web-derived evaluation panels heavily, including a train/test self-overlap inside FineWeb-2. We openly release all data, models, and code.

Vision-language models (VLMs) are increasingly deployed in multi-turn settings where users may describe visual content with incorrect assumptions. Yet existing evaluations rarely isolate how models respond when the same visually grounded false premise persists across dialogue turns. We introduce FPCO-Dialog, a benchmark for evaluating correction and cooperation behavior in VLMs under repeated false premises. FPCO-Dialog contains 1,080 images and 10,800 question turns, stratified by visual complexity, object category, and false-premise class, and uses a 10-turn protocol in which a correct dialogue prefix is followed by repeated false-premise referring expressions. We evaluate 20 commercial and open-source VLMs with a model-agnostic protocol and CorrTP@K, a correction-rate metric over false-premise turns, scored by two independent detectors. FPCO-Dialog reveals substantial and persistent cross-model differences in aggregate correction tendency, model-specific turn-wise dynamics, and systematic variation across false-premise types under the benchmark's substitution distribution. The dataset, evaluation protocol, model outputs, detector labels, and code are available.