Computation and Language

Papers filed under cs.CL on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

11,641 to 11,700 of 19,351

Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection
Renato Vukovic, Hsien-chin Lin, Carel van Niekerk +5
cs.CLcs.AIcs.IRarXiv:2609.05025v12026
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
Weiwen Xu, Jia Liu, Hou Pong Chan +4
cs.LGcs.AIcs.CLarXiv:2607.14614v12026
How is ChatGPT's behavior changing over time?
Lingjiao Chen, Matei Zaharia, James Zou
cs.CLcs.AIcs.LGarXiv:2307.09009v32023
Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?
Laura van Weesep, Riccardo Tedoldi, Jens Sjölund +6
cs.CLcs.AIcs.DBarXiv:2610.01616v12026
KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
Hongling Xu, Qi Zhu, Heyuan Deng +6
cs.LGcs.AIcs.CLarXiv:2506.02208v12025
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
Akira Fukui, Dong Huk Park, Daylen Yang +3
cs.CVcs.AIcs.CLarXiv:1606.01847v32016
ClawGym II: Exploring Black-Box RL on Agent Harness
Huatong Song, Fei Bai, Ming Yang +17
cs.CLcs.AIcs.LGarXiv:2608.16798v12026
Contextualizing Hate Speech Classifiers with Post-hoc Explanation
Brendan Kennedy, Xisen Jin, Aida Mostafazadeh Davani +2
cs.CLcs.IRcs.LGarXiv:2005.02439v32020
HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation
Zhoujun Cheng, Haoyu Dong, Zhiruo Wang +6
cs.CLcs.IRarXiv:2108.06712v32021
MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models
Tongxu Luo, Jiahe Lei, Fangyu Lei +4
cs.CLarXiv:2402.12851v12024
Aligning Language Models from User Interactions
Thomas Kleine Buening, Jonas Hübotter, Barna Pásztor +3
cs.CLcs.AIcs.LGarXiv:2603.12273v12026
ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation
Wen-wai Yim, Yujuan Fu, Asma Ben Abacha +3
cs.CLarXiv:2306.02022v12023
Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs
Jiacheng Xu, Wentao Zhang, Zhiyi Lyu +4
cs.CLcs.LGarXiv:2609.03955v12026
Polite Dialogue Generation Without Parallel Data
Tong Niu, Mohit Bansal
cs.CLcs.AIcs.LGarXiv:1805.03162v12018
Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency
Sakib Shahriar, Brady Lund, Nishith Reddy Mannuru +5
cs.AIcs.CLarXiv:2407.09519v12024
A Hybrid Persian Sentiment Analysis Framework: Integrating Dependency Grammar Based Rules and Deep Neural Networks
Kia Dashtipour, Mandar Gogate, Jingpeng Li +3
cs.CLcs.LGarXiv:1909.13568v12019
Bangla Sentence Function Classification: Corpus Development, Model Benchmarking, and Interpretability
Swapnil Kundu Argha, Abdullah Al Shafi, Rowzatul Zannat +4
cs.CLcs.AIcs.LGarXiv:2609.13869v12026
MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
Renrui Zhang, Dongzhi Jiang, Yichi Zhang +8
cs.CVcs.AIcs.CLarXiv:2403.14624v22024
COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List
Luyu Gao, Zhuyun Dai, Jamie Callan
cs.IRcs.CLarXiv:2104.07186v12021
Neural Extractive Text Summarization with Syntactic Compression
Jiacheng Xu, Greg Durrett
cs.CLarXiv:1902.00863v22019
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
Ziwen Xu, Chenyan Wu, Hengyu Sun +9
cs.CLcs.AIcs.CVarXiv:2602.02343v32026
Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs
Davide Caffagni, Federico Cocchi, Nicholas Moratelli +4
cs.CVcs.AIcs.CLarXiv:2404.15406v22024
DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines
Arnav Singhvi, Manish Shetty, Shangyin Tan +4
cs.CLcs.AIcs.PLarXiv:2312.13382v22023
ModularSQL: A Runtime Guardrail for the Multiplicity Blind Spot in Text-to-SQL
Tianxin Zhou, Ruixi Lin
cs.CLarXiv:2609.29573v12026
The Second Conversational Intelligence Challenge (ConvAI2)
Emily Dinan, Varvara Logacheva, Valentin Malykh +14
cs.AIcs.CLcs.HCarXiv:1902.00098v12019
The price of debiasing automatic metrics in natural language evaluation
Arun Tejasvi Chaganty, Stephen Mussman, Percy Liang
cs.CLarXiv:1807.02202v12018
Unified Pragmatic Models for Generating and Following Instructions
Daniel Fried, Jacob Andreas, Dan Klein
cs.CLarXiv:1711.04987v32017
Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents
Mantas Lukauskas, Viktorija Šarkauskaitė
cs.CYcs.AIcs.CLarXiv:2608.14606v12026
Language Models are Open Knowledge Graphs
Chenguang Wang, Xiao Liu, Dawn Song
cs.CLcs.AIcs.LGarXiv:2010.11967v12020
End-to-end Neural Coreference Resolution
Kenton Lee, Luheng He, Mike Lewis +1
cs.CLarXiv:1707.07045v22017
Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting
Xinwei Qiang, Xiang Fang, Chang Chen +2
cs.LGcs.CLcs.ITarXiv:2608.27339v12026
Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents
Vidya Srinivas, Zachary Englhardt, Vikram Iyer +1
cs.CLarXiv:2511.07397v32025
Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias
Justin D. Norman, Michael U. Rivera, D. Alex Hughes
cs.CLarXiv:2606.19544v12026
Theory of Mind for Multi-Agent Collaboration via Large Language Models
Huao Li, Yu Quan Chong, Simon Stepputtis +4
cs.CLcs.AIarXiv:2310.10701v32023
EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning
Chuanrui Hu, Xingze Gao, Zuyi Zhou +8
cs.AIcs.CLarXiv:2601.02163v22026
When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
Leheng Sheng, Yongtao Zhang, Wenchang Ma +6
cs.CLcs.AIarXiv:2602.10560v12026
MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making
Yubin Kim, Chanwoo Park, Hyewon Jeong +7
cs.CLcs.AIcs.LGarXiv:2404.15155v32024
Transformer Accelerator (TFA): A Macro-Op INT8 Hardware Chip for Transformer Inference and Machine Translation
Shashank
cs.ARcs.CLcs.LGarXiv:2608.23582v12026
Copying explains the collective behavior of AI agents in the wild
Giordano De Marzo, Nicola Alboré, David Garcia
cs.MAcond-mat.stat-mechcs.CLarXiv:2609.09150v22026
Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
Yangning Li, Weizhi Zhang, Yuyao Yang +17
cs.CLcs.AIarXiv:2507.09477v22025
Detecting Harmful Memes and Their Targets
Shraman Pramanick, Dimitar Dimitrov, Rituparna Mukherjee +4
cs.CLcs.LGcs.MMarXiv:2110.00413v12021
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
Yu Gu, Robert Tinn, Hao Cheng +6
cs.CLcs.LGarXiv:2007.15779v62020
Drive Like a Human: Rethinking Autonomous Driving with Large Language Models
Daocheng Fu, Xin Li, Licheng Wen +4
cs.ROcs.CLarXiv:2307.07162v12023
Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing
Diji Yang, Linda Zeng, Jinmeng Rao +1
cs.AIcs.CLcs.IRarXiv:2505.02811v22025
Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders
Zhongzhi Li, Xuansheng Wu, Yijiang Li +2
cs.CLcs.AIarXiv:2602.10388v42026
MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation
Bo Li, Ningyuan Deng, Tianyu Dong +3
cs.CLarXiv:2604.16943v12026
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Young-Jun Lee, Seungone Kim, Minki Kang +5
cs.CLcs.LGarXiv:2606.29082v12026
Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs
Kasumi Ban
cs.HCcs.CLcs.CYarXiv:2608.16467v12026
Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches
Clément Christophe, Praveen K Kanithi, Prateek Munjal +13
cs.CLarXiv:2404.14779v12024
A Dataset for Answering Time-Sensitive Questions
Wenhu Chen, Xinyi Wang, William Yang Wang
cs.CLcs.AIarXiv:2108.06314v52021
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Deyao Zhu, Xin Zhou, Shengling Qin +44
cs.CLcs.LGarXiv:2607.05155v12026
Better speech synthesis through scaling
James Betker
cs.SDcs.CLeess.ASarXiv:2305.07243v22023
word2vec Parameter Learning Explained
Xin Rong
cs.CLarXiv:1411.2738v42014
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
Binbin Zheng, Xing Ma, Yiheng Liang +6
cs.LGcs.AIcs.CLarXiv:2604.10688v22026
Reevaluating Adversarial Examples in Natural Language
John X. Morris, Eli Lifland, Jack Lanchantin +2
cs.CLcs.AIcs.CRarXiv:2004.14174v32020
ChatGPT: The End of Online Exam Integrity?
Teo Susnjak
cs.AIcs.CLarXiv:2212.09292v12022
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
Langlin Huang, Chengsong Huang, Jinyuan Li +3
cs.AIcs.CLcs.LGarXiv:2605.05566v12026
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +316
cs.CLcs.AIarXiv:2606.19348v12026
Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
Sonia Raychaudhuri, Saim Wani, Shivansh Patel +2
cs.CVcs.CLcs.ROarXiv:2109.15207v12021
Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
Zonghan Yang, Shengjie Wang, Kelin Fu +18
cs.AIcs.CLcs.SEarXiv:2509.23045v32025

Computation and Language

Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization

How is ChatGPT's behavior changing over time?

Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning

Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding

ClawGym II: Exploring Black-Box RL on Agent Harness

Contextualizing Hate Speech Classifiers with Post-hoc Explanation

HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation

MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models

Aligning Language Models from User Interactions

ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation

Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs

Polite Dialogue Generation Without Parallel Data

Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency

A Hybrid Persian Sentiment Analysis Framework: Integrating Dependency Grammar Based Rules and Deep Neural Networks

Bangla Sentence Function Classification: Corpus Development, Model Benchmarking, and Interpretability

MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List

Neural Extractive Text Summarization with Syntactic Compression

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics

Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs

DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines

ModularSQL: A Runtime Guardrail for the Multiplicity Blind Spot in Text-to-SQL

The Second Conversational Intelligence Challenge (ConvAI2)

The price of debiasing automatic metrics in natural language evaluation

Unified Pragmatic Models for Generating and Following Instructions

Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents

Language Models are Open Knowledge Graphs

End-to-end Neural Coreference Resolution

Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting

Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents

Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias

Theory of Mind for Multi-Agent Collaboration via Large Language Models

EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making

Transformer Accelerator (TFA): A Macro-Op INT8 Hardware Chip for Transformer Inference and Machine Translation

Copying explains the collective behavior of AI agents in the wild

Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs

Detecting Harmful Memes and Their Targets

Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing

Drive Like a Human: Rethinking Autonomous Driving with Large Language Models

Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing

Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders

MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs

Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches

A Dataset for Answering Time-Sensitive Questions

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

Better speech synthesis through scaling

word2vec Parameter Learning Explained

SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting

Reevaluating Adversarial Examples in Natural Language

ChatGPT: The End of Online Exam Integrity?

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments

Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents