Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computation and Language

cs.CL Watch Computation and Language

Monday 11 May

Computation and Language

Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering

Makbule Gulcin Ozsoy

Large language models (LLMs) allow users to query databases using natural language by translating questions into executable queries. Despite strong progress on tasks such as Text2SQL, Text2SPARQL, and Text2Cypher, most existing methods focus on better prompting, fine-tuning, or iterative refinement. However, they often do not explicitly enforce structural constraints, such as syntactic validity and schema consistency. This can reduce reliability, since generated queries must satisfy both syntax rules and database schema constraints to be executable. In this work, we study how structured constraints can be used in test-time inference for Text2Cypher. We focus on post-generation validation to improve query correctness. We extend a confidence-based inference framework with a sequential filtering process that combines confidence scoring, grammar validation, and schema constraints before final aggregation. This lets us analyze how different constraint types affect generated queries. Our experiments with two instruction-tuned models show that grammar-based filtering improves syntactic validity. Schema-aware filtering further improves execution quality by enforcing consistency with the database structure. However, stronger filtering also increases the number of empty predictions and reduces execution coverage. Overall, we show that adding simple structural checks at test time improves the reliability of Text2Cypher generation, and we provide a clearer view of how syntax and schema constraints contribute differently.
Read the full abstract

Computation and Language

Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding

Anton Bazdyrev, Ivan Bashtovyi, Ivan Havlytskyi et al. (+2 more)

We participated in the Fifth UNLP shared task on multi-domain document understanding, where systems must answer Ukrainian multiple-choice questions from PDF collections and localize the supporting document and page. We propose a retrieval-augmented pipeline built around three ideas: contextual chunking of PDFs, question-aware dense retrieval and reranking conditioned on both the question and answer options, and constrained answer generation from a small set of reranked passages. Our final system uses Qwen3-Embedding-8B for retrieval, a fine-tuned Qwen3-Reranker-8B for passage ranking, and Qwen3-32B for answer selection. On a held-out split, reranking improves Recall@1 from 0.6957 to 0.7935, while using the top-2 reranked passages raises answer accuracy from 0.9348 to 0.9674. Our best leaderboard run reached 0.9452 on the public leaderboard and 0.9598 on the private leaderboard. Our results suggest that, under strict code-competition constraints, preserving document structure and making relevance estimation aware of the answer space are more effective than adding complex downstream heuristics.
Read the full abstract

All authors Anton Bazdyrev, Ivan Bashtovyi, Ivan Havlytskyi, Oleksandr Kharytonov, Artur Khodakovskyi

Computation and Language

DECO-MWE: building a linguistic resource of Korean multiword expressions for feature-based sentiment analysis

Jaeho Han, Changhoe Hwang, Seongyong Choi et al. (+3 more)

This paper aims to construct a linguistic resource of Korean Multiword Expressions for Feature-Based Sentiment Analysis (FBSA): DECO-MWE. Dealing with multiword expressions (MWEs) has been a critical issue in FBSA since many constructs reveal lexical idiosyncrasy. To construct linguistic resources of sentiment MWEs efficiently, we utilize the Local Grammar Graph (LGG) methodology: DECO-MWE is formalized as a Finite-State Transducer that represents lexical-syntactic restrictions on MWEs. In this study, we built a corpus of cosmetics review texts, which show particularly frequent occurrences of MWEs. Based on an empirical examination of the corpus, four types of MWEs have been distinguished. The DECO-MWE thus covers the following four categories: Standard Polarity MWEs (SMWEs), Domain-Dependent Polarity MWEs (DMWEs), Compound Named Entity MWEs (EMWEs) and Compound Feature MWEs (FMWEs). The retrieval performance of the DECO-MWE shows 0.806 f-measure in the test corpus. This study brings a twofold outcome: first, a sizeable general-purpose polarity MWE lexicon, which may be broadly used in FBSA; second, a finite-state methodology adopted in this study to treat domain-dependent MWEs such as idiosyncratic polarity expressions, named entity expressions or feature expressions, and which may be reused in describing linguistic properties of other corpus domains.
Read the full abstract

All authors Jaeho Han, Changhoe Hwang, Seongyong Choi, Gwanghoon Yoo, Eric Laporte, Jeesun Nam

Computation and Language

MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading

Baibei Ji, Xiaoyang Weng, Juntao Li et al. (+3 more)

Long-context reasoning tasks have motivated agent-memory approaches that process document chunks sequentially while maintaining a dynamically updated memory, avoiding the quadratic complexity of standard attention. Existing methods often rely on retrieval to recover information discarded during memory overwriting, but remain vulnerable to evidence loss during memory formation and interference from invalid queries. To overcome these limitations, we propose MemReread. Built upon streaming reading, it circumvents intermediate retrieval, triggering question decomposition and targeted rereading when the final memory is insufficient. By recovering indirect evidence that may have been prematurely discarded, MemReread enables non-linear reasoning while preserving the logical flow of document comprehension. We further introduce a reinforcement learning framework that improves length extrapolation and adaptively determines the number of rereading passes according to task complexity, enabling flexible control of computational overhead. Our MemReread-4B outperforms strong baselines on long-context reasoning tasks (e.g., +1.6pp v.s. DeepSeek-V4-Pro on 2WikiMultiHopQA) while maintaining linear time complexity with respect to context length.
Read the full abstract

All authors Baibei Ji, Xiaoyang Weng, Juntao Li, Zecheng Tang, Yihang Lou, Min Zhang

Computation and Language

Building Korean linguistic resource for NLU data generation of banking app CS dialog system

Jeongwoo Yoon, On-yu Park, Changhoe Hwang et al. (+3 more)

Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increase the coverage of diverse utterances. In this study, we report the construction of a linguistic resource named FIAD (Financial Annotated Dataset) and its use to generate a Korean annotated training data for NLU in the banking customer service (CS) domain. By an empirical examination of a corpus of banking app reviews, we identified three linguistic patterns occurring in Korean request utterances: TOPIC (ENTITY, FEATURE), EVENT, and DISCOURSE MARKER. We represented them in LGGs (Local Grammar Graphs) to generate annotated data covering diverse intents and entities. To assess the practicality of the resource, we evaluate the performances of DIET-only (Intent: 0.91 /Topic [entity+feature]: 0.83), DIET+ HANBERT (I:0.94/T:0.85), DIET+ KoBERT (I:0.94/T:0.86), and DIET+ KorBERT (I:0.95/T:0.84) models trained on FIAD-generated data to extract various types of semantic items.
Read the full abstract

All authors Jeongwoo Yoon, On-yu Park, Changhoe Hwang, Gwanghoon Yoo, Eric Laporte, Jeesun Nam

Computation and Language

Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection

Yiwen Chen, Kuan Li, Fuzhen Zhuang et al. (+6 more)

Recent advances in large language models (LLMs) have expanded the context window to beyond 128K tokens, enabling long-document understanding and multi-source reasoning. A key challenge, however, lies in choosing between retrieval-augmented generation (RAG) and long-context (LC) strategies: RAG is efficient but constrained by retrieval quality, while LC supports global reasoning at higher cost and with position sensitivity. Existing methods such as Self-Route adopt failure-driven fallback from RAG to LC, but remain passive, inefficient, and hard to interpret. We propose Pre-Route, a proactive routing framework that performs structured reasoning before answering. Using lightweight metadata (e.g., document type, length, initial snippet), Pre-Route enables task analysis, coverage estimation, and information-need prediction, producing explainable and cost-efficient routing decisions. Our study shows three key findings: (i) LLMs possess latent routing ability that can be reliably elicited with guidelines, allowing single-sample performance to approach that of multi-sample (Best-of-N) results; (ii) linear probes reveal that structured prompts sharpen the separability of the "optimal routing dimension" in representation space; and (iii) distillation transfers this reasoning structure to smaller models for lightweight deployment. Experiments on LaRA (in-domain) and LongBench-v2 (OOD) confirm that Pre-Route outperforms Always-RAG, Always-LC, and Self-Route baselines, achieving superior overall cost-effectiveness.
Read the full abstract

All authors Yiwen Chen, Kuan Li, Fuzhen Zhuang, Deqing Wang, Zhao Zhang, Liwen Zhang, Yong Jiang, Shuai Wang, Minhao Cheng

Computation and Language

Relative Score Policy Optimization for Diffusion Language Models

Zichao Yu, Shengze Xu, Bingqing Jiang et al. (+2 more)

Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. Reinforcement learning with verifiable rewards (RLVR) is a natural choice for this purpose, yet its application to dLLMs is hindered by the absence of tractable sequence-level log-ratios, which are central to standard policy optimization. The lack of tractable sequence-level log-ratios forces existing methods to rely on high-variance ELBO-based approximations, where high verifier rewards can amplify inaccurate score estimates and destabilize RL training. To overcome this issue, we propose Relative Score Policy Optimization (RSPO), a simple RLVR method that uses verifiable rewards to calibrate noisy likelihood estimates in dLLMs. The core of our algorithm relies on a key observation: a reward advantage can be interpreted not only as an update direction, but also as a target for the relative log-ratio between the current and reference policies. Accordingly, RSPO calibrates this noisy relative log-ratio estimate by comparing its reward advantage with the reward-implied target relative log-ratio, updating the policy according to the gap between the current estimate and the target rather than the raw advantage alone. Experiments on mathematical reasoning and planning benchmarks show that RSPO yields especially strong gains on planning tasks and competitive mathematical-reasoning performance.
Read the full abstract

All authors Zichao Yu, Shengze Xu, Bingqing Jiang, Wenyi Zhang, Difan Zou

Computation and Language

The Impact of Editorial Intervention on Detecting Native Language Traces

Ahmet Yavuz Uluslu, Mark Gales, Kate Knill et al. (+1 more)

Native Language Identification (NLI) is the task of determining an author's native language (L1) from their non-native writing. With the advent of human-AI co-authorship, learner texts are routinely corrected and rewritten by large language models, fundamentally altering the linguistic features NLI approaches depend on. In this paper, we investigate the robustness of L1 traces across increasing degrees of editorial intervention. By processing 450 essays from the Write & Improve 2024 (W&I) corpus through varying levels of grammatical error correction and paraphrasing, we demonstrate that L1 attribution does not depend solely on surface-level errors. Instead, the detection models appear to leverage deeper L1-related features, including unidiomatic lexico-semantic choices and pragmatic transfer. We find that minimal edits preserve these structural traces and maintain high L1 attribution accuracy. In contrast, fluency edits and paraphrasing normalize these L1 features, leading to a sharp decline in performance.
Read the full abstract

All authors Ahmet Yavuz Uluslu, Mark Gales, Kate Knill, Gerold Schneider

Computation and Language

To Redact, or not to Redact? A Local LLM Approach to Deliberative Process Privilege Classification

Maik Larooij and David Graus

Government transparency laws, like the Freedom of Information (FOIA) acts in the United States and United Kingdom, and the Woo (Open Government Act) in the Netherlands, grant citizens the right to directly request documents from the government. As these documents might contain sensitive information, such as personal information or threats to national security, the laws allow governments to redact sensitive parts of the documents prior to release. We build on prior research to perform automatic sensitivity classification for the FOIA Exemption 5 deliberative process privilege using Large Language Models (LLMs). However, processing documents not yet cleared for review via third-party cloud APIs is often legally or politically untenable. Therefore, in this work, we perform sensitivity classification with a small, local model, deployable on consumer-grade hardware (Qwen3.5 9B). We compare eight variants of applying LLMs for sentence classification, using well-known prompting techniques, and find that a combination of Chain-of-Thought prompting and few-shot prompting with error-based examples outperforms classification models of earlier work in terms of recall and F2 score. This method also closely approaches the performance of a widely-used, cost-efficient commercial model (Gemini 2.5 Flash). In an additional analysis, we find that sentences that are predicted as deliberative contain more verbs that indicate the expression of opinions, and are more often phrased in in first-person. Above all, deliberativeness seems characterized by the presence of a combination of multiple indicators, in particular the combination of first-person words with a verb for expressing opinion.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

Task-Aware Calibration: Provably Optimal Decoding in LLMs

Tim Tomov, Dominik Fuchsgruber, Rajeev Verma et al. (+1 more)

LLM decoding often relies on the model's predictive distribution to generate an output. Consequently, misalignment with respect to the true generating distribution leads to suboptimal decisions in practice. While a natural solution is to calibrate the model's output distribution, for LLMs, this is ill-posed at the combinatorially vast level of free-form language. We address this by building on the insight that in many tasks, these free-form outputs can be interpreted in a semantically meaningful latent structure, for example, discrete class labels, integers, or sets. We introduce task calibration as a paradigm to calibrate the model's predictive distribution in the task-induced latent space. We apply a decision-theoretic result to show that Minimum Bayes Risk (MBR) decoding on the task-calibrated latent distribution is the optimal decoding strategy on latent model beliefs. Empirically, it consistently improves generation quality across different tasks and baselines. We also introduce Task Calibration Error (TCE), an application-aware calibration metric that quantifies the excess loss due to miscalibration. Our work demonstrates that task calibration enables more reliable model decisions across various tasks and applications.
Read the full abstract

All authors Tim Tomov, Dominik Fuchsgruber, Rajeev Verma, Stephan Günnemann

Computation and Language

How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue

Hui Lu, Xueyuan Chen, Huimeng Wang et al. (+4 more)

Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (LLMs), which are designed to extend a single coherent sequence and do not naturally support user input arriving during generation. We argue that how the user stream is routed into the LLM is therefore a key architectural question for full-duplex modeling. To study this question, we extend a text-only LLM into a unified full-duplex spoken dialogue system and compare two routing strategies under a shared training pipeline: (i) channel fusion, which injects the user stream directly into the LLM input, and (ii) cross-attention routing, which keeps the user stream as external memory accessed through cross-attention adapters. Experiments on spoken question answering and full-duplex interaction benchmarks reveal a clear tradeoff. Channel fusion yields stronger semantic grounding and consistently better question-answering performance. However, under semantically overlapping conditions such as user interruptions, it is more vulnerable to context corruption: if the model fails to stop in time, the overlapping user stream can interfere with ongoing generation and lead to semantically incoherent continuations. Cross-attention routing underperforms on question answering, but better preserves the LLM generation context and is more robust to this failure mode. These results establish user-stream routing as a central design axis in full-duplex spoken dialogue and offer practical guidance on the tradeoff between semantic integration and context robustness. We provide a demo page for qualitative inspection.
Read the full abstract

All authors Hui Lu, Xueyuan Chen, Huimeng Wang, Shuhai Peng, Shiyin Kang, Xixin Wu, Zhiyong Wu

Computation and Language

LegalCiteBench: Evaluating Citation Reliability in Legal Language Models

Sijia Chen, Hang Yin and Shunfan Zhou

Large language models (LLMs) are increasingly integrated into legal drafting and research workflows, where incorrect citations or fabricated precedents can cause serious professional harm. Existing legal benchmarks largely emphasize statutory reasoning, contract understanding, or general legal question answering, but they do not directly study a central common-law failure mode: when asked to provide case authorities without external grounding, models may return plausible-looking but incorrect citations or cases. We introduce LegalCiteBench, a benchmark for studying closed-book citation recovery, citation verification, and case matching in legal language models. LegalCiteBench contains approximately 24K evaluation instances constructed from 1,000 real U.S. judicial opinions from the Case Law Access Project. The benchmark covers five citation-centric tasks: citation retrieval, citation completion, citation error detection, case matching, and case verification and correction. Across 21 LLMs, exact citation recovery remains highly challenging in this closed-book setting: even the strongest models score below 7/100 on citation retrieval and completion. Within the evaluated models, scale and legal-domain pretraining provide limited gains and do not resolve this difficulty. Models also frequently provide concrete but incorrect or low-overlap authorities under our evaluation protocol, with Misleading Answer Rates (MAR) exceeding 94% for 20 of 21 evaluated models on retrieval-heavy tasks. A prompt-only abstention experiment shows that explicit uncertainty instructions reduce some confident fabrication but do not improve citation correctness. LegalCiteBench is intended as a diagnostic framework for studying authority generation failures, verification behavior, and abstention when external grounding is absent, incomplete, or bypassed.
Read the full abstract

Computation and Language · Cross-listed from cs.CV

V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning

Zhiwei Ning, Xuanang Gao, Jiaxi Cao et al. (+6 more)

Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although recent agentic approaches incorporate tool use, they often neglect critical execution feedback. Consequently, they suffer from the imagination-action-observer (IAO) bias, a misalignment between prior imagination and observer feedback that undermines reasoning stability and optimality. To bridge this gap, we introduce V-ABS, an action-observer driven beam search framework that enables deliberate reasoning through thinker-actor-observer iterations. We also propose an entropy-based adaptive weighting algorithm to mitigate the IAO bias by dynamically balancing the confidence scores between the policy priors and the observational feedback. Moreover, we construct a large-scale supervised fine-tuning (SFT) dataset comprising over 80k samples to guide the model to assign higher prior confidence to correct action paths. Extensive experiments across eight diverse benchmarks show that V-ABS achieves state-of-the-art performance, delivering an average improvement of 19.7% on the Qwen3-VL-8B baseline and consistent gains across both open-source and proprietary models.
Read the full abstract

All authors Zhiwei Ning, Xuanang Gao, Jiaxi Cao, Gengming Zhang, Shengnan Ma, Wenwen Tong, Hanming Deng, Jie Yang, Wei Liu

Computation and Language

When Reviews Disagree: Fine-Grained Contradiction Analysis in Scientific Peer Reviews

Sandeep Kumar, Yash Kamdar, Abid Hossain et al. (+3 more)

Scientific peer reviews frequently contain conflicting expert judgments, and the increasing scale of conference submissions makes it challenging for Area Chairs and editors to reliably identify and interpret such disagreements. Existing approaches typically frame reviewer disagreement as binary contradiction detection over isolated sentence pairs, abstracting away the review-level context and obscuring differences in the severity of evaluative conflict. In this work, we introduce a fine-grained formulation of reviewer contradiction analysis that operates over full peer reviews by explicitly identifying contradiction evidence spans and assigning graded disagreement intensity scores. To support this task, we present RevCI, an expert-annotated benchmark of peer-review pairs with evidence-level contradiction annotations with graded intensity labels. We further propose IMPACT, a structured multi-agent framework that integrates aspect-conditioned evidence extraction, deliberative reasoning, and adjudication to model reviewer contradictions and their intensity. To support efficient deployment, we distill IMPACT into TIDE, a small language model that predicts contradiction evidence and intensity in a single forward pass. Experimental results show that IMPACT substantially outperforms strong single-agent and generic multi-agent baselines in both evidence identification and intensity agreement, while TIDE achieves competitive performance at significantly lower inference cost.
Read the full abstract

All authors Sandeep Kumar, Yash Kamdar, Abid Hossain, Bharti Kumari, Tanik Saikh, Asif Ekbal

Computation and Language

ASTRA-QA: A Benchmark for Abstract Question Answering over Documents

Shu Wang, Shansong Zhou, Xinyang Wang et al. (+3 more)

Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents into coherent answers. However, this setting is still poorly supported by existing benchmarks and evaluation methods, which often lack stable abstract references or rely on coarse similarity metrics and unstable head-to-head comparisons. To alleviate this issue, we introduce ASTRA-QA, a benchmark for AbSTRAct Question Answering over documents. ASTRA-QA contains 869 QA instances over academic papers and news documents, covering five abstract question types and three controlled retrieval scopes. Each instance is equipped with explicit evaluation annotations, including answer topic sets, curated unsupported topics, and aligned evidence. Building on these annotations, ASTRA-QA assesses whether answers cover required key points and avoid unsupported content by directly scoring topic coverage and curated unsupported content, enabling scalable evaluation without exhaustive head-to-head comparisons. Experiments with representative Retrieval-Augmented Generation (RAG) methods spanning vanilla, graph-based, and hierarchical retrieval settings show that ASTRA-QA provides reference-grounded diagnostics for coverage, hallucination, and retrieval-scope robustness. Our dataset and code are available at https://xinyangsally.github.io/astra-benchmark.
Read the full abstract

All authors Shu Wang, Shansong Zhou, Xinyang Wang, Shiwei Wang, Hulong Wu, Yixiang Fang

Computation and Language · Cross-listed from cs.CV

MolSight: Molecular Property Prediction with Images

Aaditya Baranwal, Akshaj Gupta, Yogesh S Rawat et al. (+1 more)

Every molecule ever synthesised can be drawn as a 2D skeletal diagram, yet in modern property prediction this universally available representation has received less focus in favour of molecular graphs, 3D conformers, or billion-parameter language models, each imposing its own computational and data-engineering overhead. We present $\textbf{MolSight}$, the first systematic large-scale study of vision-based Molecular Property Prediction (MPP). Using 10 vision architectures, 7 pre-training strategies, and $2\,M$ molecule images, we evaluate performance across 10 downstream tasks spanning physical-property regression, drug-discovery classification, and quantum-chemistry prediction. To account for the wide variation in structural complexity across pre-training molecules, we further propose a $\textbf{chemistry-informed curriculum}$: five structural complexity descriptors partition the corpus into five tiers of increasing chemical difficulty, consistently outperforming non-curriculum baselines. We show that a single rendered bond-line image, processed by a vision encoder, is sufficient for competitive molecular property prediction, i.e. $\textit{chemical insight from sight alone}$. The best curriculum-trained configuration achieves the top result on $\textbf{5 of 10}$ benchmarks and top two on $\textbf{all 10}$, at $\textbf{$\textit{80$\times$ lower}$}$ FLOPs than the nearest multi-modal competitor.
Read the full abstract

All authors Aaditya Baranwal, Akshaj Gupta, Yogesh S Rawat, Shruti Vyas

Computation and Language

NyayaAI: An AI-Powered Legal Assistant Using Multi-Agent Architecture and Retrieval-Augmented Generation

Deepanshu, Divi Saxena, Deepali Rana et al. (+2 more)

Legal information in India remains largely inaccessible due to the complexity of legal language and the sheer volume of legal documentation involved in research and case analysis. This paper presents NyayaAI, an AI-powered legal assistant that automates and simplifies legal workflows for lawyers, law students, and general users. The system combines Large Language Models with a Retrieval-Augmented Generation pipeline grounded in a curated Indian legal knowledge base comprising constitutional provisions, statutes, case laws, and judicial precedents. A multi-agent architecture orchestrated through the Mastra TypeScript framework coordinates a main agent with specialized sub-agents handling legal research, document summarization, case law retrieval, and drafting assistance. A compliance module validates all responses before delivery. Domain classification achieved 70% precision across test samples, with RAG retrieval precision at 74% and overall response accuracy at 72%, demonstrating that structured multi-agent LLM systems can meaningfully improve legal accessibility and workflow efficiency. The code\footnote{https://github.com/B97784/NyayaAI} is made publicly available for the benefit of the research community.
Read the full abstract

All authors Deepanshu, Divi Saxena, Deepali Rana, Ayesha Varshney, Sahinur Rahman Laskar

Computation and Language

Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data

Xu Guo, Runyu Peng, Jian Tong et al. (+4 more)

Large language models (LLMs) rely on web-scale corpora for pre-training. The noise inherent in these datasets tends to obscure meaningful patterns and ultimately degrade model performance. Data curation mitigates but cannot eliminate such noise, so pre-training corpora remain noisy in practice. We therefore study whether a lightweight pre-pre-training (PPT) stage based on synthetic data with learnable temporal structure helps resist noisy data during the pre-training (PT) stage. Across various corruption settings, our method consistently improves robustness to noise during PT, with larger relative gains at higher noise levels. For a 1B-parameter model, a synthetic PPT stage with only 65M tokens achieves the same final loss as the baseline while using up to 49% fewer natural-text PT tokens across different noise levels. Mechanistic analyses suggest PPT does not immediately suppress attention to noisy tokens. Rather, PPT-initialized models gradually downweight attention between corrupted tokens during noisy PT. This indicates that synthetic PPT inhibits noise self-modeling and shapes the subsequent optimization trajectory. Code is available at https://github.com/guox18/formal-language-prepretraining.
Read the full abstract

All authors Xu Guo, Runyu Peng, Jian Tong, Yunhua Zhou, Haijun Lv, Zhihui Lu, Qipeng Guo

Computation and Language

SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution

Xiangcheng Meng, Shu Wang and Yixiang Fang

Large Language Model (LLM)-based agents (e.g., OpenClaw) increasingly rely on reusable skill libraries to solve artifact-rich tasks such as document-centric workflows and data-intensive analysis. As these libraries grow, a few works have attempted to study the Retrieval-Augmented Execution (RAE), which often first retrieves some external skills and other knowledge, then compiles the context using retrieved skills, and finally executes the task. Existing works mainly focus on optimizing skill retrieval and task execution, and they pay little attention to how to effectively organize the selected skill evidence in a form that is compact, grounded, and immediately usable for the downstream executors to complete tasks. To fill this gap, we propose SkillRAE, a two-stage RAE approach focusing on skill-based context compilation, which consists of the offline and online stages. Specifically, in the offline indexing stage, it builds a multi-level skill graph over skill communities, skills, and reusable subunits, for capturing their relationships. In the online retrieval stage, it first performs skill-ranked retrieval with selected-subunit evidence export in the graph, and then applies rescue-aware compact compilation to recover the key evidence. Together, these components compile a coarse-ranked skill set into a task-specific context that is compact, grounded, and immediately usable. Experiments on two public benchmarks show that SkillRAE achieves a significant improvement over baselines for RAE. For example, on SkillsBench, it achieves an improvement of 11.7% over the SOTA method. Ablation studies further show that our context compilation is crucial, instead of a mere prompt addition.
Read the full abstract

Computation and Language

GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction

Ihor Stepanov, Oleksandr Lukashov, Mykhailo Shtopko et al. (+1 more)

Joint named entity recognition (NER) and relation extraction (RE) is a fundamental task in natural language processing for constructing knowledge graphs from unstructured text. While recent approaches treat NER and RE as separate tasks requiring distinct models, we introduce GLiNER-Relex, a unified architecture that extends the GLiNER framework to perform both entity recognition and relation extraction in a single model. Our approach leverages a shared bidirectional transformer encoder to jointly represent text, entity type labels, and relation type labels, enabling zero-shot extraction of arbitrary entity and relation types specified at inference time. GLiNER-Relex constructs entity pair representations from recognized spans and scores them against relation type embeddings using a dedicated relation scoring module. We evaluate our model on four standard relation extraction benchmarks: CoNLL04, DocRED, FewRel, and CrossRE, and demonstrate competitive performance against both specialized relation extraction models and large language models, while maintaining the computational efficiency characteristic of the GLiNER family. The model is released as an open-source Python package with a simple inference API that allows users to specify arbitrary entity and relation type labels at inference time and obtain both entities and relation triplets in a single call. All models and code are publicly available.
Read the full abstract

All authors Ihor Stepanov, Oleksandr Lukashov, Mykhailo Shtopko, Vivek Kalyanarangan

Computation and Language

FERA: Uncertainty-Aware Federated Reasoning for Large Language Models

Ruhan Wang, Chengkai Huang, Zhiyong Wang et al. (+6 more)

Large language models (LLMs) exhibit strong reasoning capabilities when guided by high-quality demonstrations, yet such data is often distributed across organizations that cannot centralize it due to regulatory, proprietary, or institutional constraints. We study federated reasoning, where a server improves multi-step reasoning by coordinating with heterogeneous clients holding private demonstrations, without centralized training or raw data sharing. The key challenge is that client reliability is query-dependent, while the server cannot inspect client data to determine which contributions are trustworthy. To address this, we propose Uncertainty-Aware Federated Reasoning (FERA), a training-free framework based on iterative server-client co-refinement. Across communication rounds, clients generate reasoning traces with lightweight uncertainty estimates, and the server synthesizes them into improved reasoning that is redistributed as context for the next round, progressively improving both server outputs and client-side reasoning. Within each round, Uncertainty-Aware Self-Critique Aggregation (UA-SCA) resolves conflicts among heterogeneous client traces through query-dependent trust weighting and structured cross-client verification. Rather than simply discarding low-quality traces, UA-SCA revises flawed reasoning steps to recover useful information. We provide theoretical guarantees showing that the proposed iterative protocol converges and that uncertainty-aware weighting accelerates convergence. Experiments on multiple reasoning benchmarks show that FERA consistently outperforms both federated training and training-free baselines, achieving progressively higher accuracy across rounds while maintaining communication and computational efficiency.
Read the full abstract

All authors Ruhan Wang, Chengkai Huang, Zhiyong Wang, Junda Wu, Rui Wang, Tong Yu, Julian McAuley, Lina Yao, Dongruo Zhou

Computation and Language

Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning

Yongmin Yoo, Qiongkai Xu, Zhangkai Wu et al. (+1 more)

Pre-trained language models advance patent classification and retrieval by encoding claims as flat token sequences, but they overlook the dependency hierarchy among claims. Incorporating this hierarchy into self-attention poses two challenges. First, claim dependencies include relation types with different levels of reliability, so treating them uniformly may allow noisy technical relations to interfere with more reliable legal citations. Second, claim dependencies are defined at the claim level, whereas Transformer attention operates over tokens, making direct structural injection nontrivial. We propose the Patent Heterogeneous Attention-Guided Graph Encoder (PHAGE), which constructs a typed claim graph that distinguishes legal citations from technical relations. PHAGE projects this claim-level topology into token-level attention through a connectivity mask and learnable relation-aware biases, and fine-tunes the encoder using a dual-granularity contrastive objective that combines inter-patent taxonomy with intra-patent topology. At inference, the graph-specific attention components are removed, allowing representations to be generated through a standard encoder forward pass without CDG construction. Experiments on patent classification, retrieval, and clustering show that PHAGE consistently outperforms domain-adapted and citation-aware baselines, demonstrating the value of claim-level structural guidance for graph-free patent representation learning.
Read the full abstract

All authors Yongmin Yoo, Qiongkai Xu, Zhangkai Wu, Longbing Cao

Computation and Language

NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding

Hyundong Jin and Yo-Sub Han

Controlling Large Language Models (LLMs) to prevent the generation of undesirable content, such as profanity and personally identifiable information (PII), has become increasingly critical. While earlier approaches relied on post-processing or resampling, recent research has shifted towards constrained decoding methods that control outputs during generation to mitigate high computational costs and quality degradation. However, preventing multiple forbidden hard constraints or regex constraints from appearing anywhere in the output is computationally challenging. A straightforward solution is to convert these constraints into a single automaton that tracks all forbidden patterns during decoding, but this often becomes impractically large. Standard regex engines also do not readily support the operations needed to build such a constraint, such as complement and intersection. In order to address these limitations, we propose NCO, a decoding strategy that performs online pattern matching over finite hard constraints and regex constraints, reducing computational overhead without inducing state explosion. NCO is fully compatible with standard inference strategies, including various sampling methods and beam search, while also supporting soft masking for probabilistic suppression. We empirically demonstrate its effectiveness across practical tasks, including PII and profanity suppression. Our implementation is available at https://github.com/hyundong98/NCO-Decoding .
Read the full abstract

Computation and Language

Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear

R. Thomas McCoy

Futrell and Mahowald (2025) frame the success of neural language models (LMs) as supporting gradient, usage-based linguistic theories. I argue that LMs can also instantiate theories based on formal structures - the types of theories seen in the generative tradition. This argument expands the space of theories that can be tested with LMs, potentially enabling reconciliations between usage-based and generative accounts.
Read the full abstract

Computation and Language

Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering

Xinyu Zhang, Zhicheng Dou, Deyang Li et al. (+10 more)

As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent Coordination Engineering, the ability to codify and systematically improve how multiple agents collaborate has emerged as a critical bottleneck. While single-agent skills can now be distributed as portable assets, multi-agent coordination protocols remain locked within framework-internal code or static configurations, preventing them from being shared across systems or autonomously improved over time. We propose Swarm Skills, a portable specification that extends the Anthropic Skills standard with multi-agent semantics. Swarm Skills turns multi-agent workflows into first-class, distributable assets that consist of roles, workflows, execution bounds, and a built-in semantic structure for self-evolution. To operationalize the specification's evolving nature, we present a companion self-evolution algorithm that automatically distills successful execution trajectories into new Swarm Skills and continuously patches existing ones based on multi-dimensional scoring (Effectiveness, Utilization, and Freshness), eliminating the need for human-in-the-loop oversight during the refinement process. Through an architectural compatibility analysis and a comprehensive qualitative case study using the open-source JiuwenSwarm reference implementation, we demonstrate how Swarm Skills achieves zero-adapter cross-agent portability via progressive disclosure, enabling agent teams to self-evolve their coordination strategies without framework lock-in.
Read the full abstract

All authors Xinyu Zhang, Zhicheng Dou, Deyang Li, Jianjun Tao, Shuo Cheng, Ruifeng Shi, Fangchao Liu, Enrui Hu, Yangkai Ding, Hongbo Wang, Qi Ye, Xuefeng Jin, Zhangchun Zhao

Computation and Language

Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework

Xilai Ma, Liye Zhao, Weijun Yao et al. (+3 more)

Large Language Model (LLM) personalization aims to align model behaviors with individual user preferences. Existing methods often focus on isolated user histories, neglecting the essential role of inter-user differences. We propose C-BPO, a framework that personalizes LLMs via preference-calibrated binary signals. By treating target user data as positive feedback and other users' data as an auxiliary set of implicit negative signals, C-BPO captures distinct inter-user differences. To mitigate the preference overlap issue, where shared task knowledge is erroneously penalized, we derive an objective grounded in Positive-Unlabeled (PU) learning theory. This approach purifies negative signals by subtracting “positive bias”, ensuring alignment with unique idiosyncrasies without compromising general helpfulness. Empirical experiments across various personalization tasks and backbone LLMs show C-BPO consistently outperforms baselines, demonstrating the efficacy of preference-calibrated binary signals in modeling inter-user differences.
Read the full abstract

All authors Xilai Ma, Liye Zhao, Weijun Yao, Haibing Di, Wenya Wang, Jing Li

Computation and Language · Cross-listed from cs.SE

Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables

Damon McMillan

Frontier coding agents read configuration files (CLAUDE$.$md, AGENTS$.$md, Cursor Rules) at session start and are expected to follow the conventions inside them. Practitioners assume that structural choices (file size, instruction position, file architecture, contradictions in adjacent files) measurably affect adherence. We report a systematic factorial study of these choices using four manipulated variables, measuring compliance with a trivial target annotation across 1,650 Claude Code CLI sessions (16,050 function-level observations) on two TypeScript codebases, three frontier models (primarily Sonnet 4.6, with Opus 4.6 as a CLI-matched cross-model check and Opus 4.7 reported descriptively under a CLI-version confound), and five coding tasks. We use mixed-effects models with a Bayesian companion. None of the four structural variables or three two-way interactions produces a detectable contrast after multiple-testing correction. Size and conflict nulls are supported by affirmative-null Bayes factors (BF10 between 0.05 and 0.10); position and architecture nulls are failures to reject without Bayes-factor support. The largest effect we measured is within-session: each additional function the agent generates is associated with approximately 5.6% lower odds of compliance per step (OR = 0.944) within the session-length range we tested, though the relationship is non-monotonic rather than a constant per-step effect. This reproduces on a second TypeScript codebase and on Opus 4.6 at matched configuration; it was identified during analysis rather than pre-specified. Within the conditions tested, file-structure variables did not produce detectable contrasts; compliance varies systematically between coding tasks and across each session's sequence of generated functions.
Read the full abstract

Computation and Language

PlantMarkerBench: A Multi-Species Benchmark for Evidence-Grounded Plant Marker Reasoning

Sajib Acharjee Dip, Song Li and Liqing Zhang

Cell-type-specific marker genes are fundamental to plant biology, yet existing resources primarily rely on curated databases or high-throughput studies without explicitly modeling the supporting evidence found in scientific literature. We introduce PlantMarkerBench, a multi-species benchmark for evaluating literature-grounded plant marker evidence interpretation from full-text biological papers. PlantMarkerBench is constructed using a modular curation pipeline integrating large-scale literature retrieval, hybrid search, species-aware biological grounding, structured evidence extraction, and targeted human review. The benchmark spans four plant species – Arabidopsis, maize, rice, and tomato – and contains 5,550 sentence-level evidence instances annotated for marker-evidence validity, evidence type, and support strength. We define two benchmark tasks: determining whether a candidate sentence provides valid marker evidence for a gene-cell-type pair, and classifying the evidence into expression, localization, function, indirect, or negative categories. We benchmark diverse open-weight and closed-source language models across species and prompting strategies. Although frontier models achieve relatively strong performance on direct expression evidence, performance drops substantially on functional, indirect, and weak-support evidence, with evidence-type confusion emerging as a dominant failure mode. Open-weight models additionally exhibit elevated false-positive rates under ambiguous biological contexts. PlantMarkerBench provides a challenging and reproducible evaluation framework for literature-grounded biological evidence attribution and supports future research on trustworthy scientific information extraction and AI-assisted plant biology.
Read the full abstract

Computation and Language

Speech-based Psychological Crisis Assessment using LLMs

Terumi Chiba, Yang Luo, Ziyun Cui et al. (+2 more)

Psychological support hotlines provide critical support for individuals experiencing mental health emergencies, yet current assessments largely rely on human operators whose judgments may vary with professional experience and are constrained by limited staffing resources. This paper proposes a large language model (LLM)-based framework for automated crisis level classification, a key indicator that supports many downstream tasks and improves the overall quality of hotline services. To better capture emotional signals in spoken conversations, we introduce a paralinguistic injection method that inserts identified non-verbal emotional cues into speech transcripts, enabling LLM-based reasoning to incorporate critical acoustic nuances. In addition, we propose a reasoning-enhanced training strategy that trains the model to generate diagnostic reasoning chains as an auxiliary task, which serves as a regulariser to improve classification performance. Combined with data augmentation, our final system achieves a macro F1-score of 0.802 and an accuracy of 0.805 on the three-class classification task under 5-fold cross-validation.
Read the full abstract

All authors Terumi Chiba, Yang Luo, Ziyun Cui, Yongsheng Tong, Chao Zhang

Computation and Language

Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning

Yuna Haseyama, Tomoki Ito, Hiroki Sakaji et al. (+1 more)

In high-stakes domains such as healthcare, the reliability of Large Language Models (LLMs) is critical, particularly when generating clinical insights from incident reports. This study proposes a tag-based few-shot example selection method for prompting LLMs to generate background/causal factors and preventive measures from details of the medical incidents. For our experiments, we use the Japanese Medical Incident Dataset (JMID), a structured dataset of 3,884 real-world medical accident and near-miss reports. These reports are variably annotated with a wide range of tags–some include descriptive information (e.g., "medications," "blood transfusion therapy"). We compare three few-shot example selection strategies–random sampling, cosine similarity-based selection, and our proposed tag-based method–using GPT-4o and LLaMA 3.3. Results show that the tag-based approach achieves the highest precision and most stable generation behavior, while similarity-based selection often leads to unintended outputs and safety filter activation. These findings suggest that selecting examples based on human-interpretable dataset tags can improve generation precision and stability in clinical LLM applications.
Read the full abstract

All authors Yuna Haseyama, Tomoki Ito, Hiroki Sakaji, Itsuki Noda