Computation and Language
Siyuan Zhang, Jialian Li, Yichi Zhang et al. (+3 more)
Large
Language Models have achieved remarkable performance on
reasoning tasks, motivating research into how this ability evolves during training. Prior work has primarily analyzed this
evolution via explicit generation outcomes, treating the
reasoning process as a black box and obscuring internal changes. To address this opacity, we introduce a representational perspective to investigate the dynamics of the model's internal states. Through comprehensive experiments across models at various training stages, we discover that post-training yields only limited improvement in static initial representation quality. Furthermore, we reveal that, distinct from non-
reasoning tasks,
reasoning involves a significant continuous distributional shift in representations during generation. Comparative analysis indicates that post-training empowers models to drive this transition toward a better distribution for task solving. To clarify the relationship between internal states and external outputs, statistical analysis confirms a high correlation between generation correctness and the final representations; while counterfactual experiments identify the semantics of the generated
tokens, rather than additional computation during inference or intrinsic parameter differences, as the dominant driver of the transition. Collectively, we offer a novel understanding of the
reasoning process and the effect of training on
reasoning enhancement, providing valuable insights for future model analysis and optimization.
Read the full abstract ▾
All authors Siyuan Zhang, Jialian Li, Yichi Zhang, Xiao Yang, Yinpeng Dong, Hang Su
Computation and Language
Eliciting Trustworthiness Priors of Large Language Models via Economic Games
Siyu Yan, Lusha Zhu and Jian-Qiao Zhu
One critical aspect of building human-centered, trustworthy artificial intelligence (AI) systems is maintaining calibrated trust: appropriate reliance on AI systems outperforms both overtrust (e.g., automation bias) and undertrust (e.g., disuse). A fundamental challenge, however, is how to characterize the level of trust exhibited by an AI system itself. Here, we propose a novel elicitation method based on iterated in-context learning (Zhu and Griffiths, 2024a) and apply it to elicit trustworthiness priors using the Trust Game from behavioral game theory. The Trust Game is particularly well suited for this purpose because it operationalizes trust as voluntary exposure to risk based on beliefs about another
agent, rather than self-reported attitudes. Using our method, we elicit trustworthiness priors from several leading large
language models (LLMs) and find that GPT-4.1's trustworthiness priors closely track those observed in humans. Building on this result, we further examine how GPT-4.1 responds to different player personas in the Trust Game, providing an initial characterization of how such models differentiate trust across
agent characteristics. Finally, we show that variation in elicited trustworthiness can be well predicted by a stereotype-based model grounded in perceived warmth and competence.
Read the full abstract ▾
Computation and Language
WordCraft: Scaffolding the Keyword Method for L2 Vocabulary Learning with Multimodal LLMs
Yuheng Shao, Junjie Xiong, Chaoran Wu et al. (+5 more)
Applying the keyword method for vocabulary memorization remains a significant challenge for L1 Chinese-L2 English learners. They frequently struggle to generate phonologically appropriate keywords, construct coherent associations, and create vivid mental imagery to aid long-term retention. Existing approaches, including fully automated keyword generation and outcome-oriented mnemonic aids, either compromise learner engagement or lack adequate process-oriented guidance. To address these limitations, we conducted a formative study with L1 Chinese-L2 English learners and educators (N=18), which revealed key difficulties and requirements in applying the keyword method to vocabulary learning. Building on these insights, we introduce WordCraft, a learner-centered interactive tool powered by
Multimodal Large
Language Models (MLLMs). WordCraft scaffolds the keyword method by guiding learners through keyword selection, association construction, and image formation, thereby enhancing the effectiveness of vocabulary memorization. Two user studies demonstrate that WordCraft not only preserves the generation effect but also achieves high levels of effectiveness and usability.
Read the full abstract ▾
All authors Yuheng Shao, Junjie Xiong, Chaoran Wu, Xiyuan Wang, Ziyu Zhou, Yang Ouyang, Qinyi Tao, Quan Li
Computation and Language
APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards
Kaiyan Chang, Chenwei Zhu, Yingfeng Luo et al. (+7 more)
Test-Time Scaling (TTS) has significantly enhanced the capabilities of Large
Reasoning Models (LRMs) but introduces a critical side-effect known as Overthinking. We conduct a preliminary study to rethink this phenomenon from a fine-grained perspective. We observe that LRMs frequently conduct repetitive self-verification without revision even after obtaining the final answer during the
reasoning process. We formally define this specific position where the answer first stabilizes as the
Reasoning Anchor. By analyzing pre- and post-anchor
reasoning behaviors, we uncover the structural redundancy fixed in LRMs: the meaningless repetitive verification after deriving the first complete answer, which we term the Answer-Stable Tail (AST). Motivated by this observation, we propose Anchor-based Process Reward (APR), a structure-aware reward shaping method that localizes the
reasoning anchor and penalizes exclusively the post-anchor AST. Leveraging the policy optimization
algorithm suitable for length penalties, our APR models achieved the performance-efficiency Pareto frontier at 1.5B and 7B scales averaged across five mathematical
reasoning datasets while requiring substantially fewer computational resources for RL training.
Read the full abstract ▾
All authors Kaiyan Chang, Chenwei Zhu, Yingfeng Luo, Yifu Huo, Chenglong Wang, Xiaoqian Liu, Qiaozhi He, Tong Xiao, Zhengtao Yu, Jingbo Zhu
Computation and Language
Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning
Zhipeng Chen, Xiaobo Qin, Wayne Xin Zhao et al. (+2 more)
Reinforcement learning with verifiable rewards (RLVR) has shown great potential to enhance the
reasoning ability of large
language models (LLMs). However, due to the limited amount of information provided during the RLVR process, the model can only engage in largely blind exploration, which often results in failure on challenging problems. To provide additional information for the RLVR process without relying on a teacher model, we propose A$^2$D, an Adaptive Ability Decomposing method for enhancing the effectiveness of RLVR. Specifically, we first train a decomposer via RLVR without
distillation, enabling it to decompose complex questions into a set of simpler sub-questions. Next, we use this decomposer to annotate sub-questions for each question in the training
dataset, and then train the reasoner under RLVR with sub-question guidance. To better understand A$^2$D, we first compare its performance with competitive baselines, showing its effectiveness. Next, we observe that our method functions as a plug-and-play module that can be applied to different RLVR
algorithms. Furthermore, we conduct an analysis of the decomposer, revealing how the RLVR process affects its performance and behavior, and which type of guidance is better suited for enhancing the reasoner's exploration and exploitation abilities.
Read the full abstract ▾
All authors Zhipeng Chen, Xiaobo Qin, Wayne Xin Zhao, Youbin Wu, Ji-Rong Wen
Computation and Language
Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study
Ali El Lahib, Ying-Jieh Xia, Zehan Li et al. (+2 more)
Search-engine date filters are widely used to enforce pre-cutoff
retrieval in retrospective evaluations of search-augmented forecasters. We show this approach is unreliable across two major search engines:
auditing Google Search's before: filter and DuckDuckGo's date-range filter, we find that at least one retrieved page contains major post-cutoff leakage for 71% of questions on Google and 81% on DuckDuckGo, and the answer is directly revealed for 41% and 55%, respectively. Using gpt-oss-120b to forecast with these leaky documents, we demonstrate inflated prediction accuracy (Brier score 0.10 vs. 0.24 with leak-free documents). We characterize recurring leakage mechanisms, including updated articles, related-content modules, unreliable metadata, and absence-based signals, and argue that date-restricted search on these engines is insufficient for credible retrospective evaluation. We recommend stronger
retrieval safeguards or evaluation on frozen, time-stamped web snapshots.
Read the full abstract ▾
All authors Ali El Lahib, Ying-Jieh Xia, Zehan Li, Yuxuan Wang, Xinyu Pi
Computation and Language
Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
Shengrui Li, Fei Zhao, Kaiyan Zhao et al. (+6 more)
Determining an effective data mixture is a key factor in Large
Language Model (LLM) pre-training, where models must balance general competence with proficiency on hard tasks such as math and code. However, identifying an optimal mixture remains an open challenge, as existing approaches either rely on unreliable tiny-scale proxy experiments or require prohibitively expensive large-scale exploration. To address this, we propose Decouple Searching from Training Mix (DeMix), a novel framework that leverages model merging to predict optimal data ratios. Instead of training proxy models for every sampled mixture, DeMix trains component models on candidate
datasets at scale and derives data mixture proxies via weighted model merging. This paradigm decouples search from training costs, enabling evaluation of unlimited sampled mixtures without extra training burden and thus facilitating better mixture discovery through more search trials. Extensive experiments demonstrate that DeMix breaks the trade-off between sufficiency, accuracy and efficiency, obtaining the optimal mixture with higher
benchmark performance at lower search cost. Additionally, we release the DeMix Corpora, a comprehensive 22T-
token dataset comprising high-quality pre-training data with validated mixtures to facilitate open research. Our code and DeMix Corpora is available at https://github.com/Lucius-lsr/DeMix.
Read the full abstract ▾
All authors Shengrui Li, Fei Zhao, Kaiyan Zhao, Jieying Ye, Haifeng Liu, Fangcheng Shi, Zheyong Xie, Yao Hu, Shaosheng Cao
Computation and Language
CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs
Liang Wang, Xinyi Mou, Xiaoyou Liu et al. (+2 more)
User modeling characterizes individuals through their preferences and behavioral patterns to enable personalized simulation and generation with Large
Language Models (LLMs) in contemporary approaches. However, existing methods, whether
prompt-based or training-based methods, face challenges in balancing personalization quality against computational and data efficiency. We propose a novel framework CURP, which employs a bidirectional user encoder and a discrete prototype codebook to extract multi-dimensional user traits. This design enables plug-and-play personalization with a small number of trainable parameters (about 20M parameters, about 0.2% of the total model size). Through extensive experiments on variant generation tasks, we show that CURP achieves superior performance and generalization compared to strong baselines, while offering better interpretability and scalability. The code are available at https://github.com/RaidonWong/CURP_code
Read the full abstract ▾
All authors Liang Wang, Xinyi Mou, Xiaoyou Liu, Xuanjing Huang, Zhongyu Wei
Computation and Language
MedTextWeaver: Procedural Knowledge Evolution in Agentic Medical Text Editing
Ziyan Xiao, Yinghao Zhu, Liang Peng et al. (+2 more)
Medical text editing is essential for improving communication among diverse stakeholders in clinical settings. However, adapting LLM
agents to this task remains challenging because expert supervision is often sparse, fragmented, and distributed across interacting quality dimensions. We identify that direct accumulation or
retrieval of individual feedback is insufficient for effective adaptation, as fragmented evaluations do not directly translate into a coherent understanding of medical text quality. Based on this observation, we propose MedTextWeaver, a training-free framework that transforms fragmented evaluative evidence into global quality principles and actionable procedural knowledge for medical text editing. Across three clinical text
datasets and a real-world validation experiment, MedTextWeaver consistently improves performance over strong LLM baselines and existing
memory-based adaptation approaches. Further analysis demonstrates that the learned knowledge enables more effective adaptation under limited supervision while providing an explicit and interpretable interface between expert evaluations and LLM editing behavior.
Read the full abstract ▾
All authors Ziyan Xiao, Yinghao Zhu, Liang Peng, Kyongtae T Bae, Lequan Yu
Computation and Language
EchoReview: Learning Peer Review from the Echoes of Scientific Citations
Yinuo Zhang, Dingcheng Huang, Haifeng Suo et al. (+9 more)
As the volume of scientific submissions continues to grow rapidly, traditional peer review systems are facing unprecedented scalability pressures, highlighting the urgent need for automated reviewing methods that are both scalable and reliable. Existing supervised fine-tuning approaches based on real review data are fundamentally constrained by single-source of data as well as the inherent subjectivity and inconsistency of human reviews, limiting their ability to support high-quality automated reviewers. To address these issues, we propose EchoReview, a citation-context-driven data synthesis framework that systematically mines implicit collective evaluative signals from academic citations and transforms scientific community's long-term judgments into structured review-style data. Based on this pipeline, we construct EchoReview-16K, the first large-scale, cross-conference, and cross-year citation-driven review
dataset, and train an automated reviewer, EchoReviewer-7B. Experimental results demonstrate that EchoReviewer-7B can achieve significant and stable improvements on core review dimensions such as evidence support and review comprehensiveness, validating citation context as a robust and effective data paradigm for reliable automated peer review.
Read the full abstract ▾
All authors Yinuo Zhang, Dingcheng Huang, Haifeng Suo, Yizhuo Li, Ziya Zhao, Junhao Xu, Zhiying Tu, Dianhui Chu, Deming Zhai, Xianming Liu, Xiaoyan Yu, Dianbo Sui
Computation and Language · Cross-listed from cs.AI
From Prompt to Graph: Comparing LLM-Based Information Extraction Strategies in Domain-Specific Ontology Development
Xuan Liu, Ziyu Li, Mu He et al. (+10 more)
Ontologies are essential for structuring domain knowledge, improving accessibility, sharing, and reuse. However, traditional ontology construction relies on manual annotation and conventional natural
language processing (NLP) techniques, making the process labour-intensive and costly, especially in specialised fields like casting manufacturing. The rise of Large
Language Models (LLMs) offers new possibilities for automating knowledge extraction. This study investigates three LLM-based approaches, including pre-trained LLM-driven method, in-context learning (ICL) method and fine-tuning method to extract terms and relations from domain-specific texts using limited data. We compare their performances and use the best-performing method to build a casting ontology that validated by domian expert.
Read the full abstract ▾
All authors Xuan Liu, Ziyu Li, Mu He, Ziyang Ma, Xiaoxu Wu, Gizem Yilmaz, Yiyuan Xia, Bingbing Li, He Tan, Jerry Ying Hsi Fuh, Wen Feng Lu, Anders E.W. Jarfors, Per Jansson
Computation and Language
Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation
Lakshan Cooray, Deshan Sumanathilaka and Pattigadapa Venkatesh Raju
Customer-service question answering (QA) systems increasingly rely on conversational
language understanding. While Large
Language Models (LLMs) achieve strong performance, their high computational cost and deployment constraints limit practical use in resource-constrained environments. Small
Language Models (SLMs) provide a more efficient alternative, yet their effectiveness for multi-turn customer-service QA remains underexplored, particularly in scenarios requiring dialogue continuity and contextual understanding. This study investigates instruction-tuned SLMs for context-summarized multi-turn customer-service QA, using a history summarization strategy to preserve essential conversational state. We also introduce a conversation stage-based qualitative analysis to evaluate model behavior across different phases of customer-service interactions. Nine instruction-tuned low-parameterized SLMs are evaluated against three commercial LLMs using lexical and semantic similarity metrics alongside qualitative assessments, including human evaluation and LLM-as-a-judge methods. Results show notable variation across SLMs, with some models demonstrating near-LLM performance, while others struggle to maintain dialogue continuity and contextual
alignment. These findings highlight both the potential and current limitations of low-parameterized
language models for real-world customer-service QA systems.
Read the full abstract ▾
Computation and Language
LegalOne: A Family of Foundation Models for Reliable Legal Reasoning
Haitao Li, Yifan Chen, Shuo Miao et al. (+13 more)
While Large
Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain knowledge and complexity of performing rigorous multi-step judicial
reasoning. To address this gap, we present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain. LegalOne is developed through a comprehensive three-phase pipeline designed to master legal
reasoning. First, during mid-training phase, we propose Plasticity-Adjusted Sampling (PAS) to address the challenge of domain adaptation. This perplexity-based scheduler strikes a balance between the acquisition of new knowledge and the retention of original capabilities, effectively establishing a robust legal foundation. Second, during supervised fine-tuning, we employ Legal Agentic CoT
Distillation (LEAD) to distill explicit
reasoning from raw legal texts. Unlike naive
distillation, LEAD utilizes an agentic workflow to convert complex judicial processes into structured
reasoning trajectories, thereby enforcing factual grounding and logical rigor. Finally, we implement a Curriculum Reinforcement Learning (RL) strategy. Through a progressive reinforcement process spanning memorization, understanding, and
reasoning, LegalOne evolves from simple pattern matching to autonomous and reliable legal
reasoning. Experimental results demonstrate that LegalOne achieves state-of-the-art performance across a wide range of legal tasks, surpassing general-purpose LLMs with vastly larger parameter counts through enhanced knowledge density and efficiency. We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI, paving the way for deploying trustworthy and interpretable foundation models in high-stakes judicial applications.
Read the full abstract ▾
All authors Haitao Li, Yifan Chen, Shuo Miao, Qian Dong, Jia Chen, Yiran Hu, Junjie Chen, Minghao Qin, Yueyue Wu, Yujia Zhou, Qingyao Ai, Yiqun Liu, Cheng Luo, Quan Zhou, Ya Zhang, Jikun Hu
Computation and Language
Formal Semantic Control over Language Models
Yingji Zhang
This thesis advances semantic representation learning to render
language representations or models more semantically and geometrically interpretable, and to enable localised, quasi-symbolic, compositional control through deliberate shaping of their latent space geometry. We pursue this goal within a VAE framework, exploring two complementary research directions: (i) Sentence-level learning and control: disentangling and manipulating specific semantic features in the latent space to guide sentence generation, with explanatory text serving as the testbed; and (ii)
Reasoning-level learning and control: isolating and steering inference behaviours in the latent space to control NLI. In this direction, we focus on Explanatory NLI tasks, in which two premises (explanations) are provided to infer a conclusion. The overarching objective is to move toward
language models whose internal semantic representations can be systematically interpreted, precisely structured, and reliably directed. We introduce a set of novel theoretical frameworks and practical methodologies, together with corresponding experiments, to demonstrate that our approaches enhance both the interpretability and controllability of latent spaces for natural
language across the thesis.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
Louis Schiekiera, Max Zimmer, Christophe Roux et al. (+2 more)
We investigate the extent to which an LLM's hidden-state geometry can be recovered from its behavior in psycholinguistic experiments. Across eight instruction-tuned
transformer models, we run two experimental paradigms – similarity-based forced choice and free association – over a shared 5,000-word vocabulary, collecting 17.5M+ trials to build behavior-based similarity
matrices. Using representational similarity analysis, we compare behavioral geometries to layerwise hidden-state similarity and
benchmark against FastText, BERT, and cross-model consensus. We find that forced-choice behavior aligns substantially more with hidden-state geometry than free association. In a held-out-words regression, behavioral similarity (especially forced choice) predicts unseen hidden-state similarities beyond lexical baselines and cross-model consensus, indicating that behavior-only measurements retain recoverable information about internal semantic geometry. Finally, we discuss implications for the ability of behavioral tasks to uncover hidden cognitive states.
Read the full abstract ▾
All authors Louis Schiekiera, Max Zimmer, Christophe Roux, Sebastian Pokutta, Fritz Günther
Computation and Language
Jailbreaking LLMs via Calibration
Yuxuan Lu, Yongkang Guo and Yuqing Kong
Safety
alignment in Large
Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety
alignment on next-
token prediction is modeled as a systematic distortion of a pre-
alignment distribution. We cast Weak-to-Strong Jailbreaking as a forecast aggregation problem and derive an optimal aggregation strategy characterized by a Gradient Shift in the loss-induced dual space. We show that logit-arithmetic jailbreaking methods are a special case of this framework under cross-
entropy loss, and derive a broader family of aggregation rules corresponding to other proper losses. We also propose a new hybrid aggregation rule. Evaluations across red-teaming
benchmarks and math utility tasks using frontier models demonstrate that our approach achieves superior Attack Success Rates and lower "Jailbreak Tax" compared with existing methods, especially on the safety-hardened gpt-oss-120b.
Read the full abstract ▾
Computation and Language
Nsrin Ashraf, Mariam Labib and Hamada Nayel
This paper describes a system that has been submitted to the "PolyHope-M" at RANLP2025. In this work various
transformers have been implemented and evaluated for hope
speech detection for English and Germany. RoBERTa has been implemented for English, while the
multilingual model XLM-RoBERTa has been implemented for both English and German
languages. The proposed system using RoBERTa reported a weighted f1-score of 0.818 and an accuracy of 81.8% for English. On the other hand, XLM-RoBERTa achieved a weighted f1-score of 0.786 and an accuracy of 78.5%. These results reflects the importance of improvement of pre-trained large
language models and how these models enhancing the performance of different natural
language processing tasks.
Read the full abstract ▾
Computation and Language
Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars
Yitong Zhang, Yongmin Li, Yuetong Liu et al. (+4 more)
Diffusion Large
Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal
languages defined by context-free grammars, such as source code and chemical expressions. However, as probabilistic models, they still struggle to generate syntactically valid outputs reliably. A natural and promising direction to address this issue is to adapt constrained decoding techniques to enforce grammatical correctness during generation. However, applying these techniques faces two primary obstacles. On the one hand, the non-autoregressive nature of dLLMs renders most existing constrained decoding approaches inapplicable. On the other hand, current approaches specifically designed for dLLMs may allow intermediate outputs that are impossible to complete into valid sentences, which significantly limits their reliability in practice. To address these challenges, we present LAVE, a constrained decoding approach specifically designed for dLLMs. Our approach leverages a key property of dLLMs, namely their ability to predict
token distributions for all positions in parallel during each forward pass. Whenever a new
token is proposed by model, LAVE performs lookahead using these distributions to efficiently and reliably verify the validity of the proposed
token. This design ensures reliable constraints by reliably preserving the potential for intermediate outputs to be extended into valid sentences. Extensive experiments across four widely used dLLMs and three representative
benchmarks demonstrate that LAVE consistently outperforms existing baselines and achieves substantial improvements in syntactic correctness, while incurring negligible runtime overhead.
Read the full abstract ▾
All authors Yitong Zhang, Yongmin Li, Yuetong Liu, Jia Li, Xiaoran Jia, Zherui Li, Ge Li
Computation and Language
Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling
Chaoqun Cui, Shijing Wang, Liangbin Huang et al. (+4 more)
Interlingual subtitling, which translates subtitles of visual media into a target
language, is essential for entertainment localization but has not yet been explored in machine translation. Although Large
Language Models (LLMs) have significantly advanced the general capabilities of machine translation, the distinctive characteristics of subtitle texts pose persistent challenges in interlingual subtitling, particularly regarding semantic coherence, pronoun and terminology translation, and translation expressiveness. To address these issues, we present Hermes, an LLM-based automated subtitling framework. Hermes integrates three modules: Speaker Diarization, Terminology Identification, and Expressiveness Enhancement, which effectively tackle the above challenges. Experiments demonstrate that Hermes achieves state-of-the-art diarization performance and generates expressive, contextually coherent translations, thereby advancing research in interlingual subtitling.
Read the full abstract ▾
All authors Chaoqun Cui, Shijing Wang, Liangbin Huang, Qingqing Gu, Zhaolong Huang, Xiao Zeng, Wenji Mao
Computation and Language
Kanade: A Simple Disentangled Tokenizer for Spoken Language Modeling
Zhijie Huang, Stephen McIntosh, Daisuke Saito et al. (+1 more)
A good
language model starts with a good tokenizer. Tokenization is especially important for
speech modeling, which must handle continuous signals that mix linguistic and non-linguistic information. A
speech tokenizer should extract phonetics and prosody, suppress linguistically irrelevant information like speaker identity, and enable high-quality synthesis. We present Kanade, a single-layer disentangled
speech tokenizer that realizes this ideal. Kanade separates out acoustic constants to create a single stream of
tokens that captures rich phonetics and prosody. It does so without the need for auxiliary methods that existing disentangled codecs often rely on. Experiments show that Kanade achieves state-of-the-art speaker disentanglement and lexical availability, while maintaining excellent reconstruction quality.
Read the full abstract ▾
All authors Zhijie Huang, Stephen McIntosh, Daisuke Saito, Nobuaki Minematsu
Computation and Language
The French Drama Revolution: Political Economy and Literary Production, 1700-1900
Thiago Dumont Oliveira
This paper investigates the changing nature of French drama between 1700-1900 using Latent Dirichlet Allocation and Jensen-Shannon Divergence. Results indicate that the topical distribution of French drama changed profoundly after the French Revolution, particularly between 1789 and 1850. Bourgeois themes emerged among the most prevalent topics since the late 18th century. To assess the coevolution of drama and economic growth, I plot the yearly prevalence of topics alongside French GDP between 1700-1900, and discuss these changes in light of the political and economic changes prompted by the French Revolution and the industrialization of the country.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Unmasking Reasoning Processes: A Process-aware Benchmark for Evaluating Structural Mathematical Reasoning in LLMs
Xiang Zheng, Weiqi Zhai, Wei Wang et al. (+15 more)
Recent large
language models (LLMs) achieve near-saturation accuracy on many established mathematical
reasoning benchmarks, raising concerns about their ability to diagnose genuine
reasoning competence. This saturation largely stems from the dominance of template-based computation and shallow arithmetic decomposition in existing
datasets, which underrepresent
reasoning skills such as multi-constraint coordination, constructive logical synthesis, and spatial inference. To address this gap, we introduce ReasoningMath-Plus, a
benchmark of 150 carefully curated problems explicitly designed to evaluate structural
reasoning. Each problem emphasizes
reasoning under interacting constraints, constructive solution formation, or non-trivial structural insight, and is annotated with a minimal
reasoning skeleton to support fine-grained process-level evaluation. Alongside the
dataset, we introduce HCRS (Hazard-aware Chain-based Rule Score), a deterministic step-level scoring function, and train a Process Reward Model (PRM) on the annotated
reasoning traces. Empirically, while leading models attain relatively high final-answer accuracy (up to 5.8/10), HCRS-based holistic evaluation yields substantially lower scores (average 4.36/10, best 5.14/10), showing that answer-only metrics can overestimate
reasoning robustness.
Read the full abstract ▾
All authors Xiang Zheng, Weiqi Zhai, Wei Wang, Boyu Yang, Wenbo Li, Ruixiang Luo, Haoxiang Sun, Yucheng Wang, Zhengze Li, Meng Wang, Yuetian Du, Guojie Lin, Yaxuan Wang, Xiaoxiao Xu, Yanhu Mo, Xuan Ren, Hu Wei, Bing Zhao
Computation and Language
A Hierarchical and Attentional Analysis of Argument Structure Constructions in BERT Using Naturalistic Corpora
Liu Kaipeng and Wu Ling
This study investigates how the Bidirectional Encoder Representations from
Transformers model processes four fundamental Argument Structure Constructions. We employ a multi-dimensional analytical framework, which integrates MDS, t-SNE as dimensionality reduction, Generalized Discrimination Value (GDV) as cluster separation metrics, Fisher Discriminant Ratio (FDR) as linear diagnostic probing, and
attention mechanism analysis. Our results reveal a hierarchical representational structure. Construction-specific information emerges in early layers, forms maximally separable clusters in middle layers, and is maintained through later processing stages.
Read the full abstract ▾
Computation and Language
Reasoning by Commented Code for Table Question Answering
Seho Pyo, Jiheon Seok and Jaejin Lee
Table Question Answering (TableQA) poses a significant challenge for large
language models (LLMs) because conventional linearization of tables often disrupts the two-dimensional relationships intrinsic to structured data. Existing methods, which depend on end-to-end answer generation or single-line program queries, typically exhibit limited numerical accuracy and reduced interpretability. This work introduces a commented, step-by-step code-generation framework that incorporates explicit
reasoning into the Python program-generation process. The approach decomposes TableQA
reasoning into multi-line executable programs with concise natural
language comments, thereby promoting clearer
reasoning and increasing the likelihood of generating correct code. On the WikiTableQuestions
benchmark, the proposed method achieves 70.9% accuracy using Qwen2.5-Coder-7B-Instruct, surpassing the Repanda baseline (67.6%). Integrating the proposed framework with a robust end-to-end TableQA model via a lightweight answer-selection mechanism yields further improvements. This combined approach achieves up to 84.3% accuracy on the WikiTableQuestions
benchmark.
Read the full abstract ▾
Computation and Language
Culturally-Grounded Governance for Multilingual Language Models: Rights, Data Boundaries, and Accountable AI Design
Hanjing Shi and Dominic DiFranzo
Multilingual large
language models (MLLMs) are increasingly deployed across cultural, linguistic, and political contexts, yet existing governance frameworks largely assume English-centric data, homogeneous user populations, and abstract notions of
fairness. This creates systematic risks for low-resource
languages and culturally marginalized communities, where data practices, model behavior, and accountability mechanisms often fail to align with local norms, rights, and expectations. Drawing on cross-cultural perspectives in human-centered computing and AI governance, this paper synthesizes existing evidence on
multilingual model behavior, data asymmetries, and sociotechnical harm, and articulates a culturally grounded governance framework for MLLMs. We identify three interrelated governance challenges: cultural and linguistic inequities in training data and evaluation practices, misalignment between global deployment and locally situated norms, values, and power structures, and limited accountability mechanisms for addressing harms experienced by marginalized
language communities. Rather than proposing new technical
benchmarks, we contribute a conceptual agenda that reframes
multilingual AI governance as a sociocultural and rights based problem. We outline design and policy implications for data stewardship, transparency, and participatory accountability, and argue that culturally grounded governance is essential for ensuring that
multilingual language models do not reproduce existing global inequalities under the guise of scale and neutrality.
Read the full abstract ▾
Computation and Language
From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas
Zhaokun Yan, Shan Xu, Wuzheng Dong et al. (+10 more)
Public health
reasoning requires population level inference grounded in scientific evidence, expert consensus, and safety constraints. However, it remains underexplored as a structured machine learning problem with limited supervised signals and
benchmarks. We introduce GlobalHealthAtlas, a large scale
multilingual dataset of 280,210 instances spanning 15 public health domains and 17
languages. We further propose a large
language model (LLM) assisted construction and quality control pipeline with
retrieval, deduplication, evidence grounding checks, and label validation to improve consistency at scale. Finally, we present a domain aligned evaluator distilled from high confidence judgments of diverse LLMs to assess outputs along six dimensions: Accuracy,
Reasoning, Completeness, Consensus
Alignment, Terminology Norms, and Insightfulness. Together, these contributions enable reproducible training and evaluation of LLMs for safety critical public health
reasoning beyond conventional QA
benchmarks. We publicly release project codebase, evaluator, and model at:: https://github.com/Jan8217/GlobalHealthAtlas, https://huggingface.co/aerovane0/GlobalHealthAtlas_Public_Evaluator and https://huggingface.co/aerovane0/GlobalHealthAtlas_Public_Model
Read the full abstract ▾
All authors Zhaokun Yan, Shan Xu, Wuzheng Dong, Zhaohan Liu, Lijie Feng, Chengxiao Dai, Chen Tianqi, Binfan Liu, Yunpu Ma, Wenting Wei, Yingting Li, Yi Zhang, Tongning Wu
Computation and Language
Intention-Adaptive LLM Fine-Tuning for Text Revision Generation
Zhexiong Liu and Diane Litman
Large
Language Models (LLMs) have achieved impressive capabilities in various context-based text generation tasks, such as summarization and
reasoning; however, their applications in intention-based generation tasks remain underexplored. One such example is revision generation, which requires the generated text to explicitly reflect the writer's actual intentions. Identifying intentions and generating desirable revisions are challenging due to their complex and diverse nature. Although prior work has employed LLMs to generate revisions with few-shot learning, they struggle with handling entangled multi-intent scenarios. While fine-tuning LLMs using intention-based instructions appears promising, it demands large amounts of annotated data, which is expensive and scarce in the revision community. To address these challenges, we propose Intention-Tuning, an intention-adaptive layer-wise LLM fine-tuning framework that dynamically selects a subset of LLM layers to learn the intentions and subsequently transfers their representations to revision generation. Experimental results suggest that Intention-Tuning is effective and efficient on small revision corpora, outperforming several PEFT baselines.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Diffusion LMs Can Approximate Optimal Infilling Lengths Implicitly
Hengchang Liu, Zhao Yang and Bing Su
Diffusion language models (DLMs) provide a bidirectional generation framework naturally suited for infilling, yet their performance is constrained by the pre-specified infilling length. In this paper, we reveal that DLMs possess an inherent ability to discover the correct infilling length. We identify two key statistical phenomena in the first-step denoising confidence: a local Oracle Peak that emerges near the ground-truth length and a systematic Length Bias that often obscures this signal. By leveraging this signal and calibrating the bias, our training-free method CAL (Calibrated Adaptive Length) enables DLMs to approximate the optimal length through an efficient search before formal decoding. Empirical evaluations demonstrate that CAL improves Pass@1 by up to 47.7% over fixed-length baselines and 40.5% over chat-based adaptive methods in code infilling, while boosting BLEU-2 and ROUGE-L by up to 8.5% and 9.9% in text infilling. These results demonstrate that CAL paves the way for robust DLM infilling without requiring any specialized training. Code is available at https://github.com/NiuHechang/Calibrated_Adaptive_Length.
Read the full abstract ▾
Computation and Language
Words that make SENSE: Sensorimotor Norms in Learned Lexical Token Representations
Abhinav Gupta, Toben H. Mintz and Jesse Thomason
While word
embeddings derive meaning from co-occurrence patterns, human
language understanding is grounded in sensory and motor experience. We present $\text{SENSE}$ $(\textbf{S}\text{ensorimotor }$ $\textbf{E}\text{mbedding }$ $\textbf{N}\text{orm }$ $\textbf{S}\text{coring }$ $\textbf{E}\text{ngine})$, a learned projection model that predicts Lancaster sensorimotor norms from word lexical
embeddings. We also conducted a behavioral study where 281 participants selected which among candidate nonce words evoked specific sensorimotor associations, finding statistically significant correlations between human selection rates and $\text{SENSE}$ ratings across 6 of the 11 modalities. Sublexical analysis of these nonce words selection rates revealed systematic phonosthemic patterns for the interoceptive norm, suggesting a path towards computationally proposing candidate phonosthemes from text data.
Read the full abstract ▾
Computation and Language
What Matters to an LLM? Behavioral and Computational Evidences from Summarization
Yongxin Zhou, Changshun Wu, Philippe Mulhem et al. (+2 more)
Large
Language Models (LLMs) are now state-of-the-art at summarization, yet the internal notion of importance that drives their information selections remains hidden. We propose to investigate this by combining behavioral and computational analyses. Behaviorally, we generate a series of length-controlled summaries for each document and derive empirical importance distributions based on how often each information unit is selected. These reveal that LLMs converge on consistent importance patterns, sharply different from pre-LLM baselines, and that LLMs cluster more by family than by size. Computationally, we identify that certain
attention heads align well with empirical importance distributions, and that middle-to-late layers are strongly predictive of importance. Together, these results provide initial insights into what LLMs prioritize in summarization and how this priority is internally represented, opening a path toward interpreting and ultimately controlling information selection in these models.
Read the full abstract ▾
All authors Yongxin Zhou, Changshun Wu, Philippe Mulhem, Didier Schwab, Maxime Peyrard