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)

2,341 to 2,400 of 11,259

How Language Models Choose Sides: Internal Representations of Instruction Hierarchy
Enrique Balp-Straffon, Chih-Hao Hsu, Rushiraj Gadhvi +3
cs.AIcs.CLcs.LGarXiv:2608.28648v12026
Tweet2Vec: Character-Based Distributed Representations for Social Media
Bhuwan Dhingra, Zhong Zhou, Dylan Fitzpatrick +2
cs.LGcs.CLarXiv:1605.03481v22016
Coding Agents are Effective Long-Context Processors
Weili Cao, Xunjian Yin, Bhuwan Dhingra +1
cs.CLcs.AIarXiv:2603.20432v12026
A parallel corpus of Python functions and documentation strings for automated code documentation and code generation
Antonio Valerio Miceli Barone, Rico Sennrich
cs.CLcs.AIarXiv:1707.02275v12017
The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning
Dylan Jayabahu, Tinuade Adeleke
cs.LGcs.AIcs.CLarXiv:2608.28859v12026
WebXSkill: Skill Learning for Autonomous Web Agents
Zhaoyang Wang, Qianhui Wu, Xuchao Zhang +12
cs.AIcs.CLarXiv:2604.13318v22026
Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
Xinyu Wang, Yong Jiang, Nguyen Bach +4
cs.CLcs.AIcs.LGarXiv:2105.03654v32021
DAWN: Dependency-Aware Fast Inference for Diffusion LLMs
Lizhuo Luo, Zhuoran Shi, Jiajun Luo +4
cs.CLarXiv:2602.06953v12026
Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents
Natchanon Pollertlam, Witchayut Kornsuwannawit
cs.CLarXiv:2603.04814v12026
MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization
Weizhi Zhang, Xiaokai Wei, Wei-Chieh Huang +4
cs.CLarXiv:2603.25973v12026
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
Deming Ding, Shichun Liu, Enhui Yang +12
cs.CLcs.AIarXiv:2601.10343v22026
CommonsenseQA 2.0: Exposing the Limits of AI through Gamification
Alon Talmor, Ori Yoran, Ronan Le Bras +4
cs.CLcs.AIcs.LGarXiv:2201.05320v12022
Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
Jinyang Li, Binyuan Hui, Reynold Cheng +7
cs.CLcs.DBarXiv:2301.07507v12023
Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency
Zhuang Ma, Michael Collins
cs.CLcs.LGstat.MEarXiv:1809.01812v12018
Cross Language Image Matching for Weakly Supervised Semantic Segmentation
Jinheng Xie, Xianxu Hou, Kai Ye +1
cs.CVcs.CLarXiv:2203.02668v22022
Scaling Beyond Masked Diffusion Language Models
Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang +4
cs.LGcs.CLarXiv:2602.15014v12026
SE-Search: Self-Evolving Search Agent via Memory and Dense Reward
Jian Li, Yizhang Jin, Dongqi Liu +9
cs.CLarXiv:2603.03293v12026
Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline
Jiawei Xu, Arief Koesdwiady, Sisong Bei +8
cs.MAcs.CLcs.LGarXiv:2601.12307v12026
Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents
Zehong Wang, Fang Wu, Hongru Wang +8
cs.AIcs.CLcs.LGarXiv:2601.22311v12026
Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning
Yihong Huang, Fei Ma, Yihua Shao +4
cs.CVcs.AIcs.CLarXiv:2602.02951v12026
Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration
Yang Deng, Lizi Liao, Liang Chen +3
cs.CLarXiv:2305.13626v22023
MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
Zixuan Ke, Yifei Ming, Austin Xu +7
cs.AIcs.CLcs.MAarXiv:2601.14652v52026
How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN
R. Thomas McCoy, Paul Smolensky, Tal Linzen +2
cs.CLarXiv:2111.09509v12021
Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts
Saman Rahbar, Xiliang Zhu, Irvin Cardoza +1
cs.CLcs.AIcs.LGarXiv:2609.00330v12026
How Identity and Opinion Shape Political Sycophancy in LLMs
Li-Ni Fu, Chang-Chih Meng, Chien-Hua Chen +2
cs.AIcs.CLcs.CYarXiv:2608.29198v12026
AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents
Xuannan Liu, Xiao Yang, Zekun Li +2
cs.CLarXiv:2601.06818v12026
End-to-End Attention based Text-Dependent Speaker Verification
Shi-Xiong Zhang, Zhuo Chen, Yong Zhao +2
cs.CLstat.MLarXiv:1701.00562v12017
MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards
Zhiyu Shen, Ziming Wu, Fuming Lai +2
cs.CLarXiv:2601.05488v42026
Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning
Jinyuan Zhang, Peng He, He Hu +2
cs.LGcs.AIcs.CLarXiv:2609.00064v12026
BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
Xinming Tu, Tianze Wang, Yingzhou +4
cs.CLcs.AIcs.SEarXiv:2604.24955v12026
Learning to Judge: LLMs Designing and Applying Evaluation Rubrics
Clemencia Siro, Pourya Aliannejadi, Mohammad Aliannejadi
cs.CLcs.LGarXiv:2602.08672v12026
Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
Zhiyuan Cheng, Longying Lai, Yue Liu
cs.CLcs.AIcs.IRarXiv:2603.26815v32026
Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization
Bharath Chintagunta, Namit Katariya, Xavier Amatriain +1
cs.CLcs.AIcs.LGarXiv:2110.07356v12021
Breaking the News: First Impressions Matter on Online News
Julio Reis, Fabrıcio Benevenuto, Pedro O. S. Vaz de Melo +3
cs.CYcs.CLarXiv:1503.07921v22015
IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs
Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu +10
cs.AIcs.CLcs.CRarXiv:2603.10521v12026
HorizonBench: Long-Horizon Personalization with Evolving Preferences
Shuyue Stella Li, Bhargavi Paranjape, Kerem Oktar +9
cs.CLcs.AIarXiv:2604.17283v12026
GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4
Tom Kocmi, Christian Federmann
cs.CLarXiv:2310.13988v12023
Theory of Mind for Multi-Agent Collaboration via Large Language Models
Huao Li, Yu Quan Chong, Simon Stepputtis +4
cs.CLcs.AIarXiv:2310.10701v32023
FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making
Yangyang Yu, Zhiyuan Yao, Haohang Li +14
cs.CLarXiv:2407.06567v32024
GPT-RE: In-context Learning for Relation Extraction using Large Language Models
Zhen Wan, Fei Cheng, Zhuoyuan Mao +4
cs.CLarXiv:2305.02105v32023
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
Wenkai Yang, Xiaohan Bi, Yankai Lin +3
cs.CRcs.AIcs.CLarXiv:2402.11208v22024
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Wenqi Zhang, Mengna Wang, Gangao Liu +10
cs.CLcs.CVarXiv:2503.21696v22025
APEX-Agents
Bertie Vidgen, Austin Mann, Abby Fennelly +21
cs.CLcs.AIcs.LGarXiv:2601.14242v32026
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Mostafa Abdou, Artur Kulmizev, Daniel Hershcovich +3
cs.CVcs.CLarXiv:2109.06129v22021
Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction
Yuzhe Zhang, Xianwei Xue, Xingyong Wu +8
cs.CLarXiv:2604.05477v12026
Counterfactual Simulation Training for Chain-of-Thought Faithfulness
Peter Hase, Christopher Potts
cs.AIcs.CLarXiv:2602.20710v22026
YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models
Junyu Lin, Meizhen Liu, Xiufeng Huang +12
cs.CLarXiv:2601.15588v22026
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Muxi Diao, Lele Yang, Wuxuan Gong +6
cs.LGcs.AIcs.CLarXiv:2601.02151v12026
Learning to Extract Coherent Summary via Deep Reinforcement Learning
Yuxiang Wu, Baotian Hu
cs.CLarXiv:1804.07036v12018
LLM Agents Making Agent Tools
Georg Wölflein, Dyke Ferber, Daniel Truhn +2
cs.CLcs.AIcs.LGarXiv:2502.11705v22025
Like trainer, like bot? Inheritance of bias in algorithmic content moderation
Reuben Binns, Michael Veale, Max Van Kleek +1
cs.CYcs.CLcs.LGarXiv:1707.01477v12017
A Mutual Information Maximization Perspective of Language Representation Learning
Lingpeng Kong, Cyprien de Masson d'Autume, Wang Ling +3
cs.CLcs.LGarXiv:1910.08350v22019
A Comprehensive Study of Knowledge Editing for Large Language Models
Ningyu Zhang, Yunzhi Yao, Bozhong Tian +19
cs.CLcs.AIcs.CVarXiv:2401.01286v52024
A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training
Zihan Qiu, Zeyu Huang, Kaiyue Wen +16
cs.CLarXiv:2601.22966v12026
Mem-T: Densifying Rewards for Long-Horizon Memory Agents
Yanwei Yue, Boci Peng, Xuanbo Fan +3
cs.LGcs.CLarXiv:2601.23014v22026
CM3: A Causal Masked Multimodal Model of the Internet
Armen Aghajanyan, Bernie Huang, Candace Ross +8
cs.CLarXiv:2201.07520v12022
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
Xingjun Ma, Yifeng Gao, Yixu Wang +45
cs.CRcs.AIcs.CLarXiv:2502.05206v62025
Fine-Grained Spoiler Detection from Large-Scale Review Corpora
Mengting Wan, Rishabh Misra, Ndapa Nakashole +1
cs.CLarXiv:1905.13416v12019
PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation
MinKeon Kim, Namjun Lee, Jaekwang Kim
cs.CLcs.AIarXiv:2609.01658v12026
Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
Guan-Ting Lin, Chen Chen, Zhehuai Chen +1
eess.AScs.CLarXiv:2604.04847v12026

Computation and Language

How Language Models Choose Sides: Internal Representations of Instruction Hierarchy

Tweet2Vec: Character-Based Distributed Representations for Social Media

Coding Agents are Effective Long-Context Processors

A parallel corpus of Python functions and documentation strings for automated code documentation and code generation

The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning

WebXSkill: Skill Learning for Autonomous Web Agents

Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

DAWN: Dependency-Aware Fast Inference for Diffusion LLMs

Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents

MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding

CommonsenseQA 2.0: Exposing the Limits of AI through Gamification

Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing

Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency

Cross Language Image Matching for Weakly Supervised Semantic Segmentation

Scaling Beyond Masked Diffusion Language Models

SE-Search: Self-Evolving Search Agent via Memory and Dense Reward

Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline

Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents

Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning

Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration

MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks

How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN

Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts

How Identity and Opinion Shape Political Sycophancy in LLMs

AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents

End-to-End Attention based Text-Dependent Speaker Verification

MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards

Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks

Learning to Judge: LLMs Designing and Applying Evaluation Rubrics

Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off

Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization

Breaking the News: First Impressions Matter on Online News

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

HorizonBench: Long-Horizon Personalization with Evolving Preferences

GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4

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

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making

GPT-RE: In-context Learning for Relation Extraction using Large Language Models

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

APEX-Agents

Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color

Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction

Counterfactual Simulation Training for Chain-of-Thought Faithfulness

YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Learning to Extract Coherent Summary via Deep Reinforcement Learning

LLM Agents Making Agent Tools

Like trainer, like bot? Inheritance of bias in algorithmic content moderation

A Mutual Information Maximization Perspective of Language Representation Learning

A Comprehensive Study of Knowledge Editing for Large Language Models

A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training

Mem-T: Densifying Rewards for Long-Horizon Memory Agents

CM3: A Causal Masked Multimodal Model of the Internet

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Fine-Grained Spoiler Detection from Large-Scale Review Corpora

PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation

Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency