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)

2,461 to 2,520 of 11,257

Extracting books from production language models
Ahmed Ahmed, A. Feder Cooper, Sanmi Koyejo +1
cs.CLcs.AIcs.LGarXiv:2601.02671v12026
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Wenkai Yang, Lei Li, Zhiyuan Zhang +3
cs.CLarXiv:2103.15543v12021
A Continuously Growing Dataset of Sentential Paraphrases
Wuwei Lan, Siyu Qiu, Hua He +1
cs.CLarXiv:1708.00391v12017
Supervised and Unsupervised Neural Approaches to Text Readability
Matej Martinc, Senja Pollak, Marko Robnik-Šikonja
cs.CLarXiv:1907.11779v32019
Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
Satyapriya Krishna, Kalpesh Krishna, Anhad Mohananey +4
cs.CLarXiv:2409.12941v32024
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Jihao Liu, Guoxiong Gao, Zeming Sun +8
cs.AIcs.CLcs.MAarXiv:2607.06447v22026
Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer
Akhilesh Sudhakar, Bhargav Upadhyay, Arjun Maheswaran
cs.CLcs.LGarXiv:1908.09368v12019
Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection
Lixing Zhu, Gabriele Pergola, Lin Gui +2
cs.CLarXiv:2106.01071v12021
The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
Jiayuan Liu, Tianqin Li, Shiyi Du +7
cs.CLcs.AIcs.GTarXiv:2605.08060v12026
The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents
Jundong Hu, Shekar Ramachandran
cs.AIcs.CLarXiv:2609.01852v12026
Self-Critical Reasoning for Robust Visual Question Answering
Jialin Wu, Raymond J. Mooney
cs.CVcs.CLarXiv:1905.09998v32019
Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
Leonardo Ranaldi, Marco Valentino, Andrè Freitas
cs.CLarXiv:2502.12616v22025
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
SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning
Hans Ole Hatzel, Ekaterina Artemova, Haimo Paul Stiemer +2
cs.CLarXiv:2604.21782v12026
Performance Evaluation of Sentiment Analysis on Text and Emoji Data Using End-to-End, Transfer Learning, Distributed and Explainable AI Models
Sirisha Velampalli, Chandrashekar Muniyappa, Ashutosh Saxena
cs.CLcs.AIarXiv:2502.13278v12025
Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning
Xinglang Zhang, Yunyao Zhang, ZeLiang Chen +3
cs.AIcs.CLcs.LOarXiv:2601.02902v22026
VGR: Visual Grounded Reasoning
Jiacong Wang, Zijian Kang, Haochen Wang +8
cs.CVcs.AIcs.CLarXiv:2506.11991v32025
OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
Xueyu Hu, Tao Xiong, Biao Yi +26
cs.AIcs.CLcs.CVarXiv:2508.04482v12025
LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards
Guanzheng Chen, Michael Qizhe Shieh, Lidong Bing
cs.CLarXiv:2603.02146v12026
Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
Sahil Sen, Akhil Kasturi, Elias Lumer +2
cs.CLarXiv:2605.15184v12026
Topological Planning with Transformers for Vision-and-Language Navigation
Kevin Chen, Junshen K. Chen, Jo Chuang +2
cs.ROcs.AIcs.CLarXiv:2012.05292v12020
A Survey on Stance Detection for Mis- and Disinformation Identification
Momchil Hardalov, Arnav Arora, Preslav Nakov +1
cs.CLcs.SIarXiv:2103.00242v32021
openXBOW - Introducing the Passau Open-Source Crossmodal Bag-of-Words Toolkit
Maximilian Schmitt, Björn W. Schuller
cs.CVcs.CLcs.IRarXiv:1605.06778v12016
OUTLETS: Output-Length Prediction from Speculative Decoding Backbones
Weihuang Wen, Yingying Liu, Yichuan Liu +5
cs.CLarXiv:2609.01068v12026
Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes
Simran Arora, Brandon Yang, Sabri Eyuboglu +4
cs.CLarXiv:2304.09433v32023
CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
Emanuel Tewolde, Xiao Zhang, David Guzman Piedrahita +2
cs.GTcs.AIcs.CLarXiv:2604.15267v22026
Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages
Michele Ciletti
cs.CLcs.AIarXiv:2609.00998v12026
Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi, Gallil Maimon, Adel Moumen +18
cs.SDcs.AIcs.CLarXiv:2506.10274v32025
The Widespread Adoption of Large Language Model-Assisted Writing Across Society
Weixin Liang, Yaohui Zhang, Mihai Codreanu +3
cs.CLarXiv:2502.09747v22025
Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques
Joel Escudé Font, Marta R. Costa-jussà
cs.CLarXiv:1901.03116v22019
Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media
Zhanyi Ding, Zhongyan Wang, Yeyubei Zhang +5
cs.CLarXiv:2503.01082v12025
Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
Xing Zhang, Guanghui Wang, Yanwei Cui +4
cs.AIcs.CLcs.MAarXiv:2604.15877v22026
Symmetry in language statistics shapes the geometry of model representations
Dhruva Karkada, Daniel J. Korchinski, Andres Nava +2
cs.LGcond-mat.dis-nncs.CLarXiv:2602.15029v32026
FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
Ziyang Fan, Keyu Chen, Ruilong Xing +3
cs.CVcs.AIcs.CLarXiv:2602.08024v12026
Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society
Firoj Alam, Shaden Shaar, Fahim Dalvi +14
cs.CLcs.CYcs.IRarXiv:2005.00033v52020
Localizing Moments in Video with Temporal Language
Lisa Anne Hendricks, Oliver Wang, Eli Shechtman +3
cs.CVcs.CLarXiv:1809.01337v12018
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
Hao Kang, Qingru Zhang, Souvik Kundu +4
cs.LGcs.AIcs.CLarXiv:2403.05527v42024
Patent Claim Generation by Fine-Tuning OpenAI GPT-2
Jieh-Sheng Lee, Jieh Hsiang
cs.CLcs.LGstat.MLarXiv:1907.02052v12019
ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains
Ziqi Zhao, Xinyu Ma, Liu Yang +6
cs.CLcs.LGarXiv:2605.28014v12026
Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
Dat Tran, Douwe Kiela
cs.CLcs.MAarXiv:2604.02460v22026
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Xiao Liang, Zhongzhi Li, Yeyun Gong +4
cs.CLarXiv:2508.14029v42025
Understanding State Preferences With Text As Data: Introducing the UN General Debate Corpus
Alexander Baturo, Niheer Dasandi, Slava J. Mikhaylov
cs.CLcs.AIstat.MLarXiv:1707.02774v12017
Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation
Johanna Angulo, Víctor Yeste, Hector Espinos-Morato
cs.CRcs.AIcs.CLarXiv:2608.29463v12026
Chain-of-Retrieval Augmented Generation
Liang Wang, Haonan Chen, Nan Yang +3
cs.IRcs.CLarXiv:2501.14342v32025
Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
Haoxiang Sun, Yingqian Min, Zhipeng Chen +2
cs.CLarXiv:2503.21380v32025
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
Dongxu Zhang, Yiding Sun, Cheng Tan +4
cs.MMcs.CLcs.CVarXiv:2601.13879v42026
Hierarchy Parsing for Image Captioning
Ting Yao, Yingwei Pan, Yehao Li +1
cs.CVcs.CLarXiv:1909.03918v22019
Advancing Reasoning in Large Language Models: Promising Methods and Approaches
Avinash Patil, Aryan Jadon
cs.CLcs.AIarXiv:2502.03671v22025
Emergent Misalignment Is Not Magical
Mingxuan Li, Qirun Dai, Heran Wang +1
cs.AIcs.CLcs.LGarXiv:2608.29118v12026
Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning
Mingwen Zhang, Jisheng Dang, Minqiang Yang +3
cs.CVcs.CLarXiv:2608.28675v12026
Evaluating and Inducing Personality in Pre-trained Language Models
Guangyuan Jiang, Manjie Xu, Song-Chun Zhu +3
cs.CLcs.AIcs.LGarXiv:2206.07550v32022
Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
Steffen Eger, Yong Cao, Jennifer D'Souza +11
cs.CLcs.AIcs.CVarXiv:2502.05151v32025
Polite Dialogue Generation Without Parallel Data
Tong Niu, Mohit Bansal
cs.CLcs.AIcs.LGarXiv:1805.03162v12018
Characterizing COVID-19 Misinformation Communities Using a Novel Twitter Dataset
Shahan Ali Memon, Kathleen M. Carley
cs.SIcs.CLarXiv:2008.00791v42020
SemEval-2026 Task 6: CLARITY -- Unmasking Political Question Evasions
Konstantinos Thomas, Giorgos Filandrianos, Maria Lymperaiou +2
cs.CLarXiv:2603.14027v22026
Towards Robust and Privacy-preserving Text Representations
Yitong Li, Timothy Baldwin, Trevor Cohn
cs.CLarXiv:1805.06093v12018
Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance
Jiasheng Ye, Peiju Liu, Tianxiang Sun +3
cs.CLcs.AIcs.LGarXiv:2403.16952v22024
Emergent Misalignment is Easy, Narrow Misalignment is Hard
Anna Soligo, Edward Turner, Senthooran Rajamanoharan +1
cs.AIcs.CLarXiv:2602.07852v12026
Efficient Test-Time Scaling via Self-Calibration
Chengsong Huang, Langlin Huang, Jixuan Leng +2
cs.LGcs.AIcs.CLarXiv:2503.00031v12025
People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
Jenna Russell, Marzena Karpinska, Mohit Iyyer
cs.CLcs.AIarXiv:2501.15654v22025

Computation and Language

Extracting books from production language models

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

A Continuously Growing Dataset of Sentential Paraphrases

Supervised and Unsupervised Neural Approaches to Text Readability

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer

Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection

The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents

The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents

Self-Critical Reasoning for Robust Visual Question Answering

Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions

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

SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning

Performance Evaluation of Sentiment Analysis on Text and Emoji Data Using End-to-End, Transfer Learning, Distributed and Explainable AI Models

Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning

VGR: Visual Grounded Reasoning

OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use

LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards

Is Grep All You Need? How Agent Harnesses Reshape Agentic Search

Topological Planning with Transformers for Vision-and-Language Navigation

A Survey on Stance Detection for Mis- and Disinformation Identification

openXBOW - Introducing the Passau Open-Source Crossmodal Bag-of-Words Toolkit

OUTLETS: Output-Length Prediction from Speculative Decoding Backbones

Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes

CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas

Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages

Discrete Audio Tokens: More Than a Survey!

The Widespread Adoption of Large Language Model-Assisted Writing Across Society

Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques

Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents

Symmetry in language statistics shapes the geometry of model representations

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society

Localizing Moments in Video with Temporal Language

GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Patent Claim Generation by Fine-Tuning OpenAI GPT-2

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Understanding State Preferences With Text As Data: Introducing the UN General Debate Corpus

Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation

Chain-of-Retrieval Augmented Generation

Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring

Hierarchy Parsing for Image Captioning

Advancing Reasoning in Large Language Models: Promising Methods and Approaches

Emergent Misalignment Is Not Magical

Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning

Evaluating and Inducing Personality in Pre-trained Language Models

Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation

Polite Dialogue Generation Without Parallel Data

Characterizing COVID-19 Misinformation Communities Using a Novel Twitter Dataset

SemEval-2026 Task 6: CLARITY -- Unmasking Political Question Evasions

Towards Robust and Privacy-preserving Text Representations

Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance

Emergent Misalignment is Easy, Narrow Misalignment is Hard

Efficient Test-Time Scaling via Self-Calibration

People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text