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)

1,981 to 2,040 of 11,207

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners
Yihong Liu, Raoyuan Zhao, Hinrich Schütze +1
cs.CLarXiv:2601.02996v22026
Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory
Sen Hu, Yuxiang Wei, Jiaxin Ran +5
cs.CLcs.AIarXiv:2601.01280v32026
From RAG to Agentic RAG for Faithful Islamic Question Answering
Gagan Bhatia, Hamdy Mubarak, Mustafa Jarrar +8
cs.CLcs.AIarXiv:2601.07528v22026
Long-Short Transformer: Efficient Transformers for Language and Vision
Chen Zhu, Wei Ping, Chaowei Xiao +4
cs.CVcs.CLcs.LGarXiv:2107.02192v32021
Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
Ziyu Yang, Guibin Chen, Yuxin Yang +2
cs.LGcs.AIcs.CLarXiv:2601.09684v12026
Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
Ziyi Zhao, Chongming Gao, Yang Zhang +5
cs.CLcs.IRarXiv:2601.12034v12026
Universal Phone Recognition with a Multilingual Allophone System
Xinjian Li, Siddharth Dalmia, Juncheng Li +8
cs.CLcs.SDeess.ASarXiv:2002.11800v12020
Can Good Writing Be Generative? Expert-Level AI Writing Emerges through Fine-Tuning on High-Quality Books
Tuhin Chakrabarty, Paramveer S. Dhillon
cs.AIcs.CLcs.HCarXiv:2601.18353v12026
WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain
Raj Sanjay Shah, Kunal Chawla, Dheeraj Eidnani +7
cs.CLcs.AIcs.LGarXiv:2211.00083v12022
Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models
Guoming Ling, Zhongzhan Huang, Yupei Lin +4
cs.CLarXiv:2601.11340v22026
Interpretation of Natural Language Rules in Conversational Machine Reading
Marzieh Saeidi, Max Bartolo, Patrick Lewis +5
cs.CLcs.LGstat.MLarXiv:1809.01494v12018
RubRIX: Rubric-Driven Risk Mitigation in Caregiver-AI Interactions
Drishti Goel, Jeongah Lee, Qiuyue Joy Zhong +5
cs.HCcs.AIcs.CLarXiv:2601.13235v12026
Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow
Yangyang Zhong, Yanmei Gu, Zhengqing Zang +14
cs.CLcs.AIcs.LGarXiv:2601.15593v22026
Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
Luyu Gao, Yunyi Zhang, Jiawei Han +1
cs.LGcs.CLcs.IRarXiv:2101.06983v22021
Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions
Usman Naseem
cs.CLarXiv:2602.11180v12026
SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing
Ziyang Ma, Guanrou Yang, Wenxi Chen +19
cs.SDcs.CLcs.MMarXiv:2601.09385v12026
One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization
Franziska Weeber, Vera Neplenbroek, Jan Batzner +1
cs.CLarXiv:2601.18572v32026
Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia
Xinya Du, Claire Cardie
cs.CLarXiv:1805.05942v12018
STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning
Juntong Ni, Shiyu Wang, Qi He +2
cs.CLarXiv:2601.03248v32026
DocDancer: Towards Agentic Document-Grounded Information Seeking
Qintong Zhang, Xinjie Lv, Jialong Wu +8
cs.CLarXiv:2601.05163v12026
Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN
Shengxian Wan, Yanyan Lan, Jun Xu +3
cs.CLcs.AIcs.LGarXiv:1604.04378v12016
SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes
Chuhan Wang, Xintong Li, Jennifer Yuntong Zhang +5
cs.CVcs.CLcs.LGarXiv:2601.05600v12026
Explanations from Large Language Models Make Small Reasoners Better
Shiyang Li, Jianshu Chen, Yelong Shen +9
cs.CLarXiv:2210.06726v12022
PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios
Xudong Lu, Huankang Guan, Yang Bo +10
cs.CVcs.CLarXiv:2601.22575v12026
Small Language Models: Survey, Measurements, and Insights
Zhenyan Lu, Xiang Li, Dongqi Cai +5
cs.CLcs.AIcs.LGarXiv:2409.15790v32024
Closing the Modality Reasoning Gap for Speech Large Language Models
Chaoren Wang, Heng Lu, Xueyao Zhang +4
cs.CLcs.SDeess.ASarXiv:2601.05543v22026
Legal Judgment Prediction via Multi-Perspective Bi-Feedback Network
Wenmian Yang, Weijia Jia, XIaojie Zhou +1
cs.CLarXiv:1905.03969v22019
Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning
Donald Ye, Max Loffgren, Om Kotadia +2
cs.CLarXiv:2602.11201v22026
Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations
Xiaoxu Ma, Xiangbo Zhang, Zhenyu Weng
cs.CLarXiv:2601.09833v12026
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing
Zhenhua Xu, Dongsheng Chen, Shuo Wang +4
cs.AIcs.CLarXiv:2601.11007v22026
Politeness Transfer: A Tag and Generate Approach
Aman Madaan, Amrith Setlur, Tanmay Parekh +6
cs.CLarXiv:2004.14257v22020
CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation
Quan Tu, Shilong Fan, Zihang Tian +1
cs.CLarXiv:2401.01275v22024
TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents
Yanyu Chen, Jiyue Jiang, Jiahong Liu +3
cs.CLarXiv:2602.21230v12026
Overview for the Second Shared Task on Language Identification in Code-Switched Data
Giovanni Molina, Fahad AlGhamdi, Mahmoud Ghoneim +4
cs.CLarXiv:1909.13016v12019
Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
Yuling Shi, Maolin Sun, Zijun Liu +4
cs.CLcs.LGarXiv:2601.11255v12026
Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
Zirui Li, Xuefeng Bai, Kehai Chen +4
cs.AIcs.CLarXiv:2602.08783v32026
Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
Xiong Wang, Yangze Li, Chaoyou Fu +5
cs.SDcs.AIcs.CLarXiv:2411.00774v52024
CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP
Libo Qin, Minheng Ni, Yue Zhang +1
cs.CLarXiv:2006.06402v22020
PrivGemo: Privacy-Preserving Dual-Tower Graph Retrieval for Empowering LLM Reasoning with Memory Augmentation
Xingyu Tan, Xiaoyang Wang, Qing Liu +4
cs.CLarXiv:2601.08739v12026
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
Jiajie Zhang, Xin Lv, Ling Feng +2
cs.CLarXiv:2601.06021v12026
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
Yibo Yan, Mingdong Ou, Yi Cao +5
cs.CLcs.CVcs.IRarXiv:2602.19549v22026
ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support
Tiantian Chen, Jiaqi Lu, Ying Shen +1
cs.CLcs.AIarXiv:2602.01885v12026
Simple Question Answering by Attentive Convolutional Neural Network
Wenpeng Yin, Mo Yu, Bing Xiang +2
cs.CLarXiv:1606.03391v22016
MuTual: A Dataset for Multi-Turn Dialogue Reasoning
Leyang Cui, Yu Wu, Shujie Liu +2
cs.CLarXiv:2004.04494v12020
Industrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems
Alexander Loth, Martin Kappes, Marc-Oliver Pahl
cs.CYcs.AIcs.CLarXiv:2601.21963v22026
Neural Arabic Question Answering
Hussein Mozannar, Karl El Hajal, Elie Maamary +1
cs.CLcs.LGarXiv:1906.05394v12019
Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
Jiwei Tang, Shilei Liu, Zhicheng Zhang +9
cs.CLarXiv:2602.01840v22026
BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation
Peng Lai, Zhihao Ou, Yong Wang +4
cs.CLcs.AIcs.SEarXiv:2602.09383v12026
Improving Neural Question Generation using Answer Separation
Yanghoon Kim, Hwanhee Lee, Joongbo Shin +1
cs.CLcs.AIcs.NEarXiv:1809.02393v22018
Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning
Fei Wu, Zhenrong Zhang, Qikai Chang +3
cs.CLarXiv:2601.03823v12026
Exploring the Use of Text Classification in the Legal Domain
Octavia-Maria Sulea, Marcos Zampieri, Shervin Malmasi +3
cs.CLarXiv:1710.09306v12017
AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering
Chun-Yi Kuan, Kai-Wei Chang, Hung-yi Lee
eess.AScs.AIcs.CLarXiv:2601.14728v12026
Confidence Estimation for LLMs in Multi-turn Interactions
Caiqi Zhang, Ruihan Yang, Xiaochen Zhu +5
cs.CLarXiv:2601.02179v22026
Language Model Behavior: A Comprehensive Survey
Tyler A. Chang, Benjamin K. Bergen
cs.CLarXiv:2303.11504v22023
Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
Xingjian Diao, Zheyuan Liu, Chunhui Zhang +6
cs.CVcs.CLarXiv:2601.04442v22026
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
Bing Liu, Gokhan Tur, Dilek Hakkani-Tur +2
cs.CLarXiv:1804.06512v12018
LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model
Yichen Zhu, Minjie Zhu, Ning Liu +3
cs.CVcs.CLarXiv:2401.02330v42024
Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks
Alon Jacovi, Avi Caciularu, Omer Goldman +1
cs.CLcs.AIarXiv:2305.10160v22023
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
Tong Zhu, Xiaoye Qu, Daize Dong +4
cs.CLarXiv:2406.16554v12024
Adaptive Information Control for Search-Augmented LLM Reasoning
Siheng Xiong, Oguzhan Gungordu, James C. Kerce +1
cs.CLarXiv:2602.01672v22026

Computation and Language

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory

From RAG to Agentic RAG for Faithful Islamic Question Answering

Long-Short Transformer: Efficient Transformers for Language and Vision

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection

Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs

Universal Phone Recognition with a Multilingual Allophone System

Can Good Writing Be Generative? Expert-Level AI Writing Emerges through Fine-Tuning on High-Quality Books

WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain

Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models

Interpretation of Natural Language Rules in Conversational Machine Reading

RubRIX: Rubric-Driven Risk Mitigation in Caregiver-AI Interactions

Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow

Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup

Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions

SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing

One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization

Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia

STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning

DocDancer: Towards Agentic Document-Grounded Information Seeking

Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN

SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes

Explanations from Large Language Models Make Small Reasoners Better

PhoStream: Benchmarking Real-World Streaming for Omnimodal Assistants in Mobile Scenarios

Small Language Models: Survey, Measurements, and Insights

Closing the Modality Reasoning Gap for Speech Large Language Models

Legal Judgment Prediction via Multi-Perspective Bi-Feedback Network

Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning

Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations

AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing

Politeness Transfer: A Tag and Generate Approach

CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation

TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents

Overview for the Second Shared Task on Language Identification in Code-Switched Data

Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering

Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP

PrivGemo: Privacy-Preserving Dual-Tower Graph Retrieval for Empowering LLM Reasoning with Memory Augmentation

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework

ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support

Simple Question Answering by Attentive Convolutional Neural Network

MuTual: A Dataset for Multi-Turn Dialogue Reasoning

Industrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems

Neural Arabic Question Answering

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming

BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation

Improving Neural Question Generation using Answer Separation

Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning

Exploring the Use of Text Classification in the Legal Domain

AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering

Confidence Estimation for LLMs in Multi-turn Interactions

Language Model Behavior: A Comprehensive Survey

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model

Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks

LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

Adaptive Information Control for Search-Augmented LLM Reasoning