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)

361 to 420 of 11,247

SparseD: Sparse Attention for Diffusion Language Models
Zeqing Wang, Gongfan Fang, Xinyin Ma +2
cs.CLarXiv:2509.24014v12025
Interactive Memory Learning for Long-Term Conversations
Cai Ke, Jiangyue Yan, Han Zhang +5
cs.AIcs.CLarXiv:2609.17088v12026
ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents
Cai Ke, Xin Liu, Han Zhang +6
cs.AIcs.CLarXiv:2609.17010v12026
Controlled Decoding from Language Models
Sidharth Mudgal, Jong Lee, Harish Ganapathy +10
cs.LGcs.AIcs.CLarXiv:2310.17022v32023
WebQA: Multihop and Multimodal QA
Yingshan Chang, Mridu Narang, Hisami Suzuki +3
cs.CLcs.AIcs.CVarXiv:2109.00590v42021
R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration
Dhruv Dixit, Paritosh Pandey
cs.CLcs.LGarXiv:2609.11955v12026
Nepali Legal Expertise through Generative and Extractive Pre-trained Transformers (NepLEGiT)
Ranjit Raut, Tishya Dhakal, Aaryan Shakya +3
cs.CLarXiv:2609.16010v12026
EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models
Michael Wornow, Rahul Thapa, Ethan Steinberg +2
cs.LGcs.AIcs.CLarXiv:2307.02028v32023
Space as an Interventional Invariant: Cross-Modal Predictive Geometry for Stratified Cities and Em-Spaced Intelligence
Tao Yang, Xuhui Lin, Kunyao Li +1
cs.LGcs.CLarXiv:2609.11959v12026
Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions
Zahra Abbasiantaeb, Yifei Yuan, Evangelos Kanoulas +1
cs.CLcs.AIcs.IRarXiv:2312.02913v12023
Japanese Stroke LLM Evaluation: A Conversational Benchmark for Safe Stroke Care in Japanese Using Large Language Models
Keisuke Masuda, Kazutaka Yatsushiro, Hirohumi Iwamoto +2
cs.CLarXiv:2609.16739v12026
Large language models effectively leverage document-level context for literary translation, but critical errors persist
Marzena Karpinska, Mohit Iyyer
cs.CLarXiv:2304.03245v32023
An Empirical Study of Counterfactual Self-Explanations in LLMs
Giannis Kalyvas, Giorgos Filandrianos, Orfeas Menis Mastromichalakis +2
cs.CLarXiv:2609.17119v12026
Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA
Kailong Fan, Anqi Pu, Yichen Wu +7
cs.CLarXiv:2609.16660v12026
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
Han Cai, Ji Lin, Yujun Lin +5
cs.LGcs.CLcs.CVarXiv:2204.11786v12022
The Router Within: Eliciting Native Skill Routing from a Frozen LLM
Ruishuo Chen, Xun Wang, Yu Chen +2
cs.LGcs.AIcs.CLarXiv:2609.15982v12026
RLP: Reinforcement as a Pretraining Objective
Ali Hatamizadeh, Syeda Nahida Akter, Shrimai Prabhumoye +5
cs.LGcs.AIcs.CLarXiv:2510.01265v22025
Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding
Mirac Suzgun, Adam Tauman Kalai
cs.CLcs.AIcs.HCarXiv:2401.12954v12024
GraphText: Graph Reasoning in Text Space
Jianan Zhao, Le Zhuo, Yikang Shen +5
cs.CLcs.LGarXiv:2310.01089v12023
Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis
Caoyun Fan, Jindou Chen, Yaohui Jin +1
cs.AIcs.CLcs.GTarXiv:2312.05488v22023
WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences
Xiao Liu, Hanyu Lai, Hao Yu +6
cs.CLcs.AIarXiv:2306.07906v12023
Contrastive Triple Extraction with Generative Transformer
Hongbin Ye, Ningyu Zhang, Shumin Deng +4
cs.CLcs.AIcs.DBarXiv:2009.06207v82020
Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech
Greta Damo, Elias Urios Alacreu, Elena Cabrio +2
cs.CLarXiv:2609.16906v12026
EASSE: Easier Automatic Sentence Simplification Evaluation
Fernando Alva-Manchego, Louis Martin, Carolina Scarton +1
cs.CLarXiv:1908.04567v22019
Latent Undertow: How Ordinary Typos Break Probes
Elad David, Max Fomin, Amit LeVi
cs.CLcs.LGarXiv:2609.15994v12026
FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering
Zhenyu Li, Sunqi Fan, Yu Gu +5
cs.CLcs.AIarXiv:2308.12060v32023
Self-Improving LLM Agents at Test-Time
Emre Can Acikgoz, Cheng Qian, Heng Ji +2
cs.LGcs.AIcs.CLarXiv:2510.07841v12025
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Hwan Chang, Yonghyun Jun, Hwanhee Lee
cs.CLarXiv:2509.22830v32025
InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
Weilin Zhao, Zihan Zhou, Zhou Su +10
cs.CLcs.AIcs.LGarXiv:2509.24663v12025
Word meaning in minds and machines
Brenden M. Lake, Gregory L. Murphy
cs.CLcs.AIcs.LGarXiv:2008.01766v32020
Verifiable Social Reasoning for LLM Assistants
Amir Taubenfeld, Zorik Gekhman, Avigail Grinstein-Dabush +6
cs.AIcs.CLarXiv:2609.17496v12026
Representing Numbers in NLP: a Survey and a Vision
Avijit Thawani, Jay Pujara, Pedro A. Szekely +1
cs.CLcs.AIcs.LGarXiv:2103.13136v12021
Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs
Toqeer Ehsan, Nico Penttilä, Richard Schmidt +2
cs.CLcs.AIarXiv:2609.17327v12026
BroRL: Scaling Reinforcement Learning via Broadened Exploration
Jian Hu, Mingjie Liu, Ximing Lu +8
cs.LGcs.CLarXiv:2510.01180v12025
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
Jon Saad-Falcon, Avanika Narayan, Hakki Orhun Akengin +12
cs.DCcs.AIcs.CLarXiv:2511.07885v62025
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Aashiq Muhamed, Mona T. Diab, Virginia Smith
cs.LGcs.CLcs.CRarXiv:2609.16204v12026
PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress
Kevin Qinghong Lin, Siyuan Hu, Pan Lu +14
cs.CLcs.MAarXiv:2609.16995v12026
Disentangling Representation Evolution in Transformers through Directional Decomposition
Shwai He, Haichao Zhang, Shen Yan
cs.CLcs.LGarXiv:2609.15975v12026
The Hydra Effect: Emergent Self-repair in Language Model Computations
Thomas McGrath, Matthew Rahtz, Janos Kramar +2
cs.LGcs.AIcs.CLarXiv:2307.15771v12023
Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training
Yuanhao Yue, Qianli Ma, Chengyu Wang +3
cs.LGcs.AIcs.CLarXiv:2609.15051v12026
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
Bowen Qin, Yi Xie, Yesheng Liu +1
cs.LGcs.CLarXiv:2609.16816v12026
Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning
Maxwell Nye, Michael Henry Tessler, Joshua B. Tenenbaum +1
cs.AIcs.CLcs.LGarXiv:2107.02794v22021
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Aashiq Muhamed, Mona T. Diab, Virginia Smith +2
cs.LGcs.AIcs.CLarXiv:2609.15029v12026
PyThaiNLP: Thai Natural Language Processing in Python
Wannaphong Phatthiyaphaibun, Korakot Chaovavanich, Charin Polpanumas +6
cs.CLarXiv:2312.04649v12023
When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis
Kaiyuan Liu, Qiuyang Mang, Bo Peng +6
cs.CLarXiv:2609.15309v12026
AgentIR: Reasoning-Aware Retrieval for Deep Research Agents
Zijian Chen, Xueguang Ma, Shengyao Zhuang +3
cs.CLarXiv:2603.04384v32026
MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
Hongjin Qian, Zheng Liu, Peitian Zhang +4
cs.CLcs.AIarXiv:2409.05591v32024
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Siwei Wu, Jincheng Ren, Yizhi Li +11
cs.CLarXiv:2609.14857v12026
Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
Ling Yang, Zhenfei Yin, Yingcheng Wu
cs.CLarXiv:2609.15973v12026
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
Zixuan Wang, Yufan Zhou, Jinzhou Tang +16
cs.CLcs.LGarXiv:2609.15972v12026
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
Ilya Koziev, Leonid Sinev, Ivan Oseledets
cs.CLcs.AIarXiv:2609.15504v12026
AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning
Liang Ding
cs.AIcs.CLarXiv:2603.21362v32026
OCNLI: Original Chinese Natural Language Inference
Hai Hu, Kyle Richardson, Liang Xu +3
cs.CLarXiv:2010.05444v12020
MS2: Multi-Document Summarization of Medical Studies
Jay DeYoung, Iz Beltagy, Madeleine van Zuylen +2
cs.CLcs.AIcs.LGarXiv:2104.06486v32021
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Sibo Zhu, Shicheng Fan, Xinyue Wang +3
cs.AIcs.CLcs.CVarXiv:2609.15364v12026
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Tong Zheng, Xidong Wu, Zheng Zhang +14
cs.CLarXiv:2609.14858v12026
RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation
Chao Jin, Zili Zhang, Xuanlin Jiang +4
cs.DCcs.CLcs.LGarXiv:2404.12457v22024
Prompting for Multimodal Hateful Meme Classification
Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong +1
cs.CLcs.IRcs.MMarXiv:2302.04156v12023
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Shuhan Xue, Jianyuan Zhong, Ziyuan Nan +10
cs.AIcs.CLarXiv:2609.17523v12026
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
Zhiwei Li, Lei Zhu, Hao Gu +6
cs.CLarXiv:2609.13141v12026

Computation and Language

SparseD: Sparse Attention for Diffusion Language Models

Interactive Memory Learning for Long-Term Conversations

ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents

Controlled Decoding from Language Models

WebQA: Multihop and Multimodal QA

R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration

Nepali Legal Expertise through Generative and Extractive Pre-trained Transformers (NepLEGiT)

EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models

Space as an Interventional Invariant: Cross-Modal Predictive Geometry for Stratified Cities and Em-Spaced Intelligence

Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions

Japanese Stroke LLM Evaluation: A Conversational Benchmark for Safe Stroke Care in Japanese Using Large Language Models

Large language models effectively leverage document-level context for literary translation, but critical errors persist

An Empirical Study of Counterfactual Self-Explanations in LLMs

Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA

Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications

The Router Within: Eliciting Native Skill Routing from a Frozen LLM

RLP: Reinforcement as a Pretraining Objective

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

GraphText: Graph Reasoning in Text Space

Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis

WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences

Contrastive Triple Extraction with Generative Transformer

Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech

EASSE: Easier Automatic Sentence Simplification Evaluation

Latent Undertow: How Ordinary Typos Break Probes

FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering

Self-Improving LLM Agents at Test-Time

ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents

InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation

Word meaning in minds and machines

Verifiable Social Reasoning for LLM Assistants

Representing Numbers in NLP: a Survey and a Vision

Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs

BroRL: Scaling Reinforcement Learning via Broadened Exploration

Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress

Disentangling Representation Evolution in Transformers through Directional Decomposition

The Hydra Effect: Emergent Self-repair in Language Model Computations

Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training

ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals

Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

PyThaiNLP: Thai Natural Language Processing in Python

When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis

AgentIR: Reasoning-Aware Retrieval for Deep Research Agents

MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Discovery Foundation Models: Toward Open-Ended Discovery Intelligence

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus

AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning

OCNLI: Original Chinese Natural Language Inference

MS2: Multi-Document Summarization of Medical Studies

RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation

Prompting for Multimodal Hateful Meme Classification

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking