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)

14,581 to 14,640 of 19,068

Length Desensitization in Direct Preference Optimization
Wei Liu, Yang Bai, Chengcheng Han +5
cs.LGcs.CLarXiv:2409.06411v22024
Base Models Beat Aligned Models at Randomness and Creativity
Peter West, Christopher Potts
cs.CLarXiv:2505.00047v22025
It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution
Rowan Hall Maudslay, Hila Gonen, Ryan Cotterell +1
cs.CLcs.CYarXiv:1909.00871v32019
Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion
Jiaqian Zhu, Yang Zhang, Junhua Ding +1
cs.CLcs.AIcs.LGarXiv:2608.22140v12026
Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds
Md. Faiyaz Abdullah Sayeedi
cs.CLarXiv:2608.17950v12026
RAG Collapse: LLM Responses Collapse When Retrieved Documents Are Self-Authored
Gregory Druck, Ethan Smith
cs.CLcs.IRarXiv:2608.22118v12026
Towards a Seamless Integration of Word Senses into Downstream NLP Applications
Mohammad Taher Pilehvar, Jose Camacho-Collados, Roberto Navigli +1
cs.CLarXiv:1710.06632v12017
CooperBench: Why Coding Agents Cannot be Your Teammates Yet
Arpandeep Khatua, Hao Zhu, Peter Tran +8
cs.LGcs.AIcs.CLarXiv:2601.13295v22026
From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
Tianle Li, Wei-Lin Chiang, Evan Frick +5
cs.LGcs.AIcs.CLarXiv:2406.11939v22024
Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence
Timothy R. McIntosh, Teo Susnjak, Nalin Arachchilage +3
cs.AIcs.CLcs.CYarXiv:2402.09880v22024
An automated pipeline for standardised speech-unit annotation in spontaneous dialogue
Hanlu He, Harald Vilhelm Skat-Rørdam, Ingvi Örnólfsson +1
cs.CLarXiv:2610.03078v12026
Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language Models
Claudiu Creanga, Ioachim Lihor, Liviu P. Dinu
cs.CLarXiv:2610.03077v12026
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Shenzhi Wang, Le Yu, Chang Gao +15
cs.CLcs.AIcs.LGarXiv:2506.01939v22025
Communicating Activations Between Language Model Agents
Vignav Ramesh, Kenneth Li
cs.CLcs.AIcs.LGarXiv:2501.14082v22025
PEARL: Parallel Speculative Decoding with Adaptive Draft Length
Tianyu Liu, Yun Li, Qitan Lv +4
cs.CLarXiv:2408.11850v32024
Code as Representation: A Compilable Parsing Paradigm for Academic Documents
Rihui Jin, Jun Wang, chengyuan zhu +11
cs.CVcs.CLarXiv:2608.17550v12026
HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation
Tiezheng Yu, Yuxin Jiang, Jinpeng Li +4
cs.CLarXiv:2610.03063v12026
A Survey of Race, Racism, and Anti-Racism in NLP
Anjalie Field, Su Lin Blodgett, Zeerak Waseem +1
cs.CLarXiv:2106.11410v22021
Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models
Nura Aljaafari, Danilo S. Carvalho, André Freitas
cs.CLarXiv:2408.11827v22024
Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey
Bonan Min, Hayley Ross, Elior Sulem +6
cs.CLcs.AIcs.LGarXiv:2111.01243v12021
BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations
Yunfan Zhou, Qiming Shi, Yizhou Yang +2
cs.AIcs.CLarXiv:2608.29345v12026
Equal Ranking Quality, Different Decisions: Training Order-Consistent LLM Scorers
Markus Frohmann, Mahdiyar Alavi, Elizabeth Lingg +1
cs.CLcs.IRcs.LGarXiv:2608.26762v12026
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
Yanwei Li, Chengyao Wang, Jiaya Jia
cs.CVcs.CLarXiv:2311.17043v12023
Sentry: Learning to Recover from LLM Agent Failures at Test Time
Changxiu Ji, Amy Lu, Qizheng Zhang +1
cs.LGcs.AIcs.CLarXiv:2610.02994v12026
Ontology-Driven Structural Regularization for Document-Level Relation Extraction
Laura Menotti, Stefano Marchesin, Gianmaria Silvello
cs.CLarXiv:2608.20856v12026
Large Language Models for Generative Information Extraction: A Survey
Derong Xu, Wei Chen, Wenjun Peng +7
cs.CLarXiv:2312.17617v32023
MuLan: A Joint Embedding of Music Audio and Natural Language
Qingqing Huang, Aren Jansen, Joonseok Lee +3
eess.AScs.CLcs.SDarXiv:2208.12415v12022
Multi-lingual Evaluation of Code Generation Models
Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang +22
cs.LGcs.CLarXiv:2210.14868v32022
PAL: Proxy-Guided Black-Box Attack on Large Language Models
Chawin Sitawarin, Norman Mu, David Wagner +1
cs.CLcs.AIcs.CRarXiv:2402.09674v12024
Word Affect Intensities
Saif M. Mohammad
cs.CLarXiv:1704.08798v22017
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
Wenbo Pan, Shujie Liu, Chin-Yew Lin +5
cs.AIcs.CLcs.LGarXiv:2606.05922v22026
Automatic Generation of Programming Exercises and Code Explanations using Large Language Models
Sami Sarsa, Paul Denny, Arto Hellas +1
cs.SEcs.AIcs.CLarXiv:2206.11861v22022
Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Risks
Zonghao Ying, Jiaqi Yan, Huize Luo +3
cs.CLarXiv:2609.27900v12026
MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning
Zhiyang Xu, Ying Shen, Lifu Huang
cs.CLarXiv:2212.10773v32022
Misinformation Without Triggers: From Factual Answers to Downstream Decisions
Lin Tian, Marian-Andrei Rizoiu
cs.CLcs.AIarXiv:2610.02886v12026
Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction
Lujia Bao, Qian Chen, Luyao Cheng +15
eess.AScs.AIcs.CLarXiv:2609.25176v22026
Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis
Wenmeng Yu, Hua Xu, Ziqi Yuan +1
cs.CLarXiv:2102.04830v12021
Param$\Delta$ for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost
Sheng Cao, Mingrui Wu, Karthik Prasad +2
cs.CLcs.AIcs.LGarXiv:2504.21023v12025
The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems
Yangze Liu, Zhongyi Han
cs.AIcs.CLcs.LGarXiv:2609.11146v12026
To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model
Xianzhi Zeng, Jiangneng Li, Gao Cong
cs.LGcs.CLarXiv:2610.02839v12026
FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training
Miaobo Hu, Shuhao Hu, Xiaobo Guo +4
cs.AIcs.CLcs.LGarXiv:2610.02828v12026
Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models
Zhiyuan Peng, Xuyang Wu, Qifan Wang +1
cs.IRcs.AIcs.CLarXiv:2307.08303v52023
Self-Instruct: Aligning Language Models with Self-Generated Instructions
Yizhong Wang, Yeganeh Kordi, Swaroop Mishra +4
cs.CLcs.AIarXiv:2212.10560v22022
Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs
Renfei Zhang, Manasa Kaniselvan, Rylan Schaeffer +1
cs.CLcs.AIarXiv:2511.05933v32025
SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
Wenxuan Wang, Haoyu Sun, Fukuan Hou +4
cs.AIcs.CLarXiv:2606.05761v22026
ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
Yandan Yang, Shuang Zeng, Tong Lin +11
cs.CVcs.CLcs.ROarXiv:2602.11236v22026
CodeRAG-Bench: Can Retrieval Augment Code Generation?
Zora Zhiruo Wang, Akari Asai, Xinyan Velocity Yu +4
cs.SEcs.CLarXiv:2406.14497v22024
SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
Thinh Pham, Nguyen Nguyen, Pratibha Zunjare +3
cs.CLcs.AIcs.LGarXiv:2506.01062v42025
CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists
Junlin Yang, Dylan Zhang, Xiangchen Song +7
cs.AIcs.CLarXiv:2605.26029v22026
Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
Hosein Hasani, Mohammadali Banayeeanzade, Ali Nafisi +5
cs.CLarXiv:2601.02989v22026
PersonaGym: Evaluating Persona Agents and LLMs
Vinay Samuel, Henry Peng Zou, Yue Zhou +6
cs.CLcs.AIcs.LGarXiv:2407.18416v52024
Optimizing Diversity and Quality through Base-Aligned Model Collaboration
Yichen Wang, Chenghao Yang, Tenghao Huang +3
cs.CLcs.AIcs.LGarXiv:2511.05650v22025
Neural Models for Documents with Metadata
Dallas Card, Chenhao Tan, Noah A. Smith
stat.MLcs.CLarXiv:1705.09296v22017
DISCO: Distilling Counterfactuals with Large Language Models
Zeming Chen, Qiyue Gao, Antoine Bosselut +2
cs.CLarXiv:2212.10534v32022
No PUN Intended: Plausible Unknown Names for Person-Centred LLM Evaluation
Dimitri Staufer, David Hartmann, Ibrahim Baroud
cs.CLcs.AIcs.LGarXiv:2608.21206v12026
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu +25
eess.AScs.CLcs.SDarXiv:2507.02768v22025
Confident at the moment of action: belief miscalibration in LLM play under hidden information
Bhushan Kashinath Joshi
cs.AIcs.CLcs.LGarXiv:2608.24691v12026
The Impact of Reasoning Step Length on Large Language Models
Mingyu Jin, Qinkai Yu, Dong Shu +5
cs.CLcs.AIarXiv:2401.04925v42024
TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
Kai Li, Xuanqing Yu, Ziyi Ni +9
cs.CLcs.AIarXiv:2601.02845v22026
MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
Qi Luo, Xiaonan Li, Yuxin Wang +4
cs.CLarXiv:2510.27569v12025

Computation and Language

Length Desensitization in Direct Preference Optimization

Base Models Beat Aligned Models at Randomness and Creativity

It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution

Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion

Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds

RAG Collapse: LLM Responses Collapse When Retrieved Documents Are Self-Authored

Towards a Seamless Integration of Word Senses into Downstream NLP Applications

CooperBench: Why Coding Agents Cannot be Your Teammates Yet

From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence

An automated pipeline for standardised speech-unit annotation in spontaneous dialogue

Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language Models

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Communicating Activations Between Language Model Agents

PEARL: Parallel Speculative Decoding with Adaptive Draft Length

Code as Representation: A Compilable Parsing Paradigm for Academic Documents

HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation

A Survey of Race, Racism, and Anti-Racism in NLP

Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models

Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey

BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations

Equal Ranking Quality, Different Decisions: Training Order-Consistent LLM Scorers

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

Sentry: Learning to Recover from LLM Agent Failures at Test Time

Ontology-Driven Structural Regularization for Document-Level Relation Extraction

Large Language Models for Generative Information Extraction: A Survey

MuLan: A Joint Embedding of Music Audio and Natural Language

Multi-lingual Evaluation of Code Generation Models

PAL: Proxy-Guided Black-Box Attack on Large Language Models

Word Affect Intensities

Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference

Automatic Generation of Programming Exercises and Code Explanations using Large Language Models

Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Risks

MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning

Misinformation Without Triggers: From Factual Answers to Downstream Decisions

Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction

Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis

Param$\Delta$ for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost

The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems

To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model

FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models

Self-Instruct: Aligning Language Models with Self-Generated Instructions

Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs

SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents

ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning

CodeRAG-Bench: Can Retrieval Augment Code Generation?

SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy

PersonaGym: Evaluating Persona Agents and LLMs

Optimizing Diversity and Quality through Base-Aligned Model Collaboration

Neural Models for Documents with Metadata

DISCO: Distilling Counterfactuals with Large Language Models

No PUN Intended: Plausible Unknown Names for Person-Centred LLM Evaluation

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment

Confident at the moment of action: belief miscalibration in LLM play under hidden information

The Impact of Reasoning Step Length on Large Language Models

TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents

MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval