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)

13,141 to 13,200 of 19,360

Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT
Qihuang Zhong, Liang Ding, Juhua Liu +2
cs.CLarXiv:2302.10198v22023
SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation
Zhi Rao, Yucheng Zhou, Qianran Sun +8
cs.CLcs.CVcs.MMarXiv:2610.11371v12026
InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
Yuchen Yan, Liang Jiang, Jin Jiang +7
cs.CLcs.AIarXiv:2602.06960v32026
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe
Xiang Yue, Huseyin A. Inan, Xuechen Li +6
cs.CLcs.CRarXiv:2210.14348v32022
SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue
Stephanie Fong, Yiwen Jiang, Zimu Wang +12
cs.CLarXiv:2609.01548v12026
Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs
Prakhar Khatri
cs.CVcs.CLarXiv:2609.03820v12026
Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
Tsz Ting Chung, Lemao Liu, Mo Yu +1
cs.CLcs.AIarXiv:2605.13511v32026
Quantifying the Gap between Understanding and Generation within Unified Multimodal Models
Chenlong Wang, Yuhang Chen, Zhihan Hu +4
cs.CLarXiv:2602.02140v12026
Deception by Omission: Language Models Knowingly Hide Their Mistakes
Lucas Florin, Amelie Knecht, Ulysse Schaller +1
cs.CLarXiv:2610.11351v12026
Jailbreaking in the Haystack
Rishi Rajesh Shah, Chen Henry Wu, Shashwat Saxena +3
cs.CRcs.AIcs.CLarXiv:2511.04707v22025
LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
Luyao Zhuang, Shengyuan Chen, Yilin Xiao +5
cs.CLarXiv:2510.10114v42025
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
Haoning Wu, Zicheng Zhang, Weixia Zhang +11
cs.CVcs.CLcs.LGarXiv:2312.17090v12023
Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering
Tharaka D. Fonseka, Niraj K. Jha
cs.CLcs.AIarXiv:2609.12230v12026
LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models
Yifan Yang, Jiajun Zhou, Ngai Wong +1
cs.CLcs.AIcs.LGarXiv:2402.11417v12024
Understanding R1-Zero-Like Training: A Critical Perspective
Zichen Liu, Changyu Chen, Wenjun Li +5
cs.LGcs.AIcs.CLarXiv:2503.20783v22025
Extremely Sparse Supervision Incentivizes Reasoning Ability
Zhishuai Liu, Xingzi Xu, Mehmet Saygin Seyfioglu +2
cs.AIcs.CLcs.LGarXiv:2609.04565v12026
How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering
Jinxin Liu, Shulin Cao, Jiaxin Shi +5
cs.CLarXiv:2401.05777v22024
HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks
Adnan El Assadi, Isaac Chung, Roman Solomatin +2
cs.CLarXiv:2510.10062v32025
Data Efficient Sample Selection for In-Context Learning
V Venktesh, Cem Levi, Avishek Anand
cs.LGcs.CLarXiv:2609.06670v22026
AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization
Yusheng Liao, Chuan Xuan, Yutong Cai +4
cs.CLarXiv:2601.13918v12026
Self-Edit: Fault-Aware Code Editor for Code Generation
Kechi Zhang, Zhuo Li, Jia Li +2
cs.SEcs.CLarXiv:2305.04087v52023
A Syntactic Neural Model for General-Purpose Code Generation
Pengcheng Yin, Graham Neubig
cs.CLcs.PLcs.SEarXiv:1704.01696v12017
Don't Throw Away Your Pretrained Model
Shangbin Feng, Wenhao Yu, Yike Wang +3
cs.CLarXiv:2510.09913v12025
From Persona to Personalization: A Survey on Role-Playing Language Agents
Jiangjie Chen, Xintao Wang, Rui Xu +15
cs.CLcs.AIarXiv:2404.18231v22024
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
Jeonghye Kim, Jiwon Jeon, Dongsheng Li +1
cs.LGcs.CLarXiv:2605.10781v12026
MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
Fangyu Liu, Francesco Piccinno, Syrine Krichene +6
cs.CLcs.AIcs.CVarXiv:2212.09662v22022
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better
Siyan Zhao, Yonggan Fu, Jindong Jiang +8
cs.CLarXiv:2610.11291v12026
PACE: A Proxy for Agentic Capability Evaluation
Yueqi Song, Lintang Sutawika, Jiarui Liu +8
cs.AIcs.CLarXiv:2607.02032v22026
Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence
Emilio Jorge, Mikael Kågebäck, Fredrik D. Johansson +1
cs.AIcs.CLcs.LGarXiv:1611.03218v42016
CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs
Nafiseh Nikeghbal, Amir Hossein Kargaran, Jana Diesner
cs.CLarXiv:2510.09871v12025
LLM-based Text Simplification and its Effect on User Comprehension and Cognitive Load
Theo Guidroz, Diego Ardila, Jimmy Li +24
cs.CLarXiv:2505.01980v12025
Rhythms of Work: Multi-Scale Interpretation of Human Behavioral Traces for Workplace Agents
Lin Ai, Scott Counts
cs.CLarXiv:2609.04556v12026
Multi-Turn On-Policy Distillation with Prefix Replay
Baohao Liao, Hanze Dong, Christof Monz +3
cs.LGcs.AIcs.CLarXiv:2607.04763v32026
Structured Neural Summarization
Patrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt
cs.LGcs.CLcs.SEarXiv:1811.01824v42018
Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence
Jiaxing Zhang, Ruyi Gan, Junjie Wang +22
cs.CLarXiv:2209.02970v32022
ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement
Mary Lynn Martin, Yifei Zhang, Martha Palmer +1
cs.CLcs.CVarXiv:2608.16011v12026
On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
Hoigi Seo, Dong Un Kang, Hyunjin Cho +2
cs.CVcs.AIcs.CLarXiv:2510.09008v12025
The unreasonable effectiveness of few-shot learning for machine translation
Xavier Garcia, Yamini Bansal, Colin Cherry +5
cs.CLarXiv:2302.01398v12023
Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
Minghan Wang, Boyuan Wang, Jinhang Zuo +2
cs.CLarXiv:2609.39578v12026
Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting
Sanyuan Chen, Yutai Hou, Yiming Cui +3
cs.CLarXiv:2004.12651v12020
FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs
Yan Wang, Keyi Wang, Shanshan Yang +12
cs.CLcs.CEcs.IRarXiv:2510.08886v32025
PersonaEdit: Representative Sample Selection for Personalized Model Editing
You-Mei Huang, Chung-Chi Chen, An-Zi Yen
cs.CLarXiv:2608.27816v12026
DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution
Shengda Fan, Xuyan Ye, Yankai Lin
cs.AIcs.CLarXiv:2601.13761v22026
A Fast and Simple Algorithm for Training Neural Probabilistic Language Models
Andriy Mnih, Yee Whye Teh
cs.CLcs.LGarXiv:1206.6426v12012
Encoded but Disconnected: Decomposing Vision-Language Model Failures under a Patching Null
Genpei Zhang
cs.CVcs.CLcs.LGarXiv:2610.00024v12026
SkillHarness: Harnessing Safe Skills for Computer-Use Agents
Yurun Chen, Biao Yi, Keting Yin +1
cs.AIcs.CLcs.CRarXiv:2606.20636v12026
Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks
Zezhong Wang, Xueyang Tang, Rui Lian +2
cs.CRcs.AIcs.CLarXiv:2609.39549v12026
Scaling the Vocabulary of Non-autoregressive Models for Efficient Generative Retrieval
Ravisri Valluri, Akash Kumar Mohankumar, Kushal Dave +4
cs.CLcs.IRcs.LGarXiv:2406.06739v12024
Large Language Models Meet NL2Code: A Survey
Daoguang Zan, Bei Chen, Fengji Zhang +5
cs.SEcs.AIcs.CLarXiv:2212.09420v22022
Learning Executable Semantic Parsers for Natural Language Understanding
Percy Liang
cs.CLcs.AIarXiv:1603.06677v12016
"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy
Yuchen Cui, Siddharth Karamcheti, Raj Palleti +3
cs.ROcs.AIcs.CLarXiv:2301.02555v12023
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Patrick Lewis, Ethan Perez, Aleksandra Piktus +9
cs.CLcs.LGarXiv:2005.11401v42020
Summaries:한국어
Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning
Andrea Gregor de Varda, Sana Pandey, Pengrui Han +2
cs.CLcs.AIarXiv:2609.04463v12026
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Terry Yue Zhuo, Xiaolong Jin, Hange Liu +37
cs.SEcs.AIcs.CLarXiv:2510.08697v22025
Conformity Breaks Conformal Prediction
Yibo Hu, Hanyu Su
cs.LGcs.CLarXiv:2609.04445v12026
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models
Mengjie Zhao, Tao Lin, Fei Mi +2
cs.CLarXiv:2004.12406v22020
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Yi Yang, Cong Qin, Xiaodan Liu +8
cs.LGcs.AIcs.CLarXiv:2608.04788v12026
Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
Zhanghao Hu, Qinglin Zhu, Runcong Zhao +4
cs.CLcs.AIarXiv:2602.02007v42026
Detecting Fake News with Capsule Neural Networks
Mohammad Hadi Goldani, Saeedeh Momtazi, Reza Safabakhsh
cs.CLcs.CYarXiv:2002.01030v12020
Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
Zhenghao Lin, Yeyun Gong, Yelong Shen +5
cs.CLcs.LGarXiv:2212.11685v22022

Computation and Language

Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT

SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning

Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe

SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue

Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs

Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

Quantifying the Gap between Understanding and Generation within Unified Multimodal Models

Deception by Omission: Language Models Knowingly Hide Their Mistakes

Jailbreaking in the Haystack

LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora

Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels

Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering

LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models

Understanding R1-Zero-Like Training: A Critical Perspective

Extremely Sparse Supervision Incentivizes Reasoning Ability

How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering

HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks

Data Efficient Sample Selection for In-Context Learning

AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization

Self-Edit: Fault-Aware Code Editor for Code Generation

A Syntactic Neural Model for General-Purpose Code Generation

Don't Throw Away Your Pretrained Model

From Persona to Personalization: A Survey on Role-Playing Language Agents

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR

MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering

When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better

PACE: A Proxy for Agentic Capability Evaluation

Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence

CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs

LLM-based Text Simplification and its Effect on User Comprehension and Cognitive Load

Rhythms of Work: Multi-Scale Interpretation of Human Behavioral Traces for Workplace Agents

Multi-Turn On-Policy Distillation with Prefix Replay

Structured Neural Summarization

Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence

ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models

The unreasonable effectiveness of few-shot learning for machine translation

Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?

Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting

FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs

PersonaEdit: Representative Sample Selection for Personalized Model Editing

DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution

A Fast and Simple Algorithm for Training Neural Probabilistic Language Models

Encoded but Disconnected: Decomposing Vision-Language Model Failures under a Patching Null

SkillHarness: Harnessing Safe Skills for Computer-Use Agents

Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks

Scaling the Vocabulary of Non-autoregressive Models for Efficient Generative Retrieval

Large Language Models Meet NL2Code: A Survey

Learning Executable Semantic Parsers for Natural Language Understanding

"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Conformity Breaks Conformal Prediction

Masking as an Efficient Alternative to Finetuning for Pretrained Language Models

Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

Detecting Fake News with Capsule Neural Networks

Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise