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)

12,361 to 12,420 of 19,405

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
Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
Sandeep Subramanian, Adam Trischler, Yoshua Bengio +1
cs.CLarXiv:1804.00079v12018
Evaluating Factuality in Generation with Dependency-level Entailment
Tanya Goyal, Greg Durrett
cs.CLarXiv:2010.05478v22020
Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?
Abhishek Das, Harsh Agrawal, C. Lawrence Zitnick +2
cs.CVcs.CLarXiv:1606.03556v22016
Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Tasks
Xiangyu Wang, Jin Wu, Xiaoyu Li +2
cs.CLarXiv:2609.03432v12026
A Comparative Study on End-to-end Speech to Text Translation
Parnia Bahar, Tobias Bieschke, Hermann Ney
cs.CLcs.LGeess.ASarXiv:1911.08870v12019
Improving the Accuracy of Pre-trained Word Embeddings for Sentiment Analysis
Seyed Mahdi Rezaeinia, Ali Ghodsi, Rouhollah Rahmani
cs.CLcs.IRarXiv:1711.08609v12017
LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals
Gilat Toker, Nitay Calderon, Ohad Amosy +1
cs.CLcs.AIarXiv:2601.10700v22026
Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game
Silin Du, Xiaowei Zhang
cs.CLcs.AIcs.HCarXiv:2404.01602v22024
Towards General Agentic Intelligence via Environment Scaling
Runnan Fang, Shihao Cai, Baixuan Li +13
cs.CLarXiv:2509.13311v12025
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
Shuang Sun, Huatong Song, Yuhao Wang +10
cs.CLcs.AIcs.IRarXiv:2505.16834v32025
GRIFFIN: Effective Token Alignment for Faster Speculative Decoding
Shijing Hu, Jingyang Li, Xingyu Xie +3
cs.CLcs.AIarXiv:2502.11018v32025
OCNLI: Original Chinese Natural Language Inference
Hai Hu, Kyle Richardson, Liang Xu +3
cs.CLarXiv:2010.05444v12020
CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
Hansi Zeng, Liam Collins, Bhuvesh Kumar +2
cs.AIcs.CLcs.IRarXiv:2604.17555v22026
Identifying beneficial task relations for multi-task learning in deep neural networks
Joachim Bingel, Anders Søgaard
cs.CLarXiv:1702.08303v12017
TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
Wenhao Wu, Menghao Zhang, Xin Wang +3
cs.CLcs.AIarXiv:2608.22793v12026
LocAgent: Graph-Guided LLM Agents for Code Localization
Zhaoling Chen, Xiangru Tang, Gangda Deng +6
cs.SEcs.AIcs.CLarXiv:2503.09089v22025
Yi: Open Foundation Models by 01.AI
01. AI, :, Alex Young +30
cs.CLcs.AIarXiv:2403.04652v32024
Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems
Jesse Dodge, Andreea Gane, Xiang Zhang +5
cs.CLcs.LGarXiv:1511.06931v62015
Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
Ziyu Yang, Guibin Chen, Yuxin Yang +2
cs.LGcs.AIcs.CLarXiv:2601.09684v12026
Large Language Model Reasoning Failures
Peiyang Song, Pengrui Han, Noah Goodman
cs.AIcs.CLcs.LGarXiv:2602.06176v12026
Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes
Rahul Khedar, Mayank Malhotra, Avinash Karn
cs.AIcs.CLcs.MAarXiv:2609.29952v12026
Answering Complex Open-domain Questions Through Iterative Query Generation
Peng Qi, Xiaowen Lin, Leo Mehr +2
cs.CLarXiv:1910.07000v12019
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
Jiashu Xu, Mingyu Derek Ma, Fei Wang +2
cs.CLcs.AIcs.CRarXiv:2305.14710v22023
Politeness Transfer: A Tag and Generate Approach
Aman Madaan, Amrith Setlur, Tanmay Parekh +6
cs.CLarXiv:2004.14257v22020
Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples
Hezekiah J. Branch, Jonathan Rodriguez Cefalu, Jeremy McHugh +5
cs.CLarXiv:2209.02128v12022
Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
Yu Wu, Wei Wu, Chen Xing +2
cs.CLarXiv:1612.01627v22016
JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
Jiangshan Duo, Hanyu Li, Hailin Zhang +3
cs.CLcs.AIcs.LGarXiv:2601.08468v12026
A Survey of Multimodal Retrieval-Augmented Generation
Lang Mei, Siyu Mo, Zhihan Yang +1
cs.IRcs.AIcs.CLarXiv:2504.08748v12025
MemoryBank: Enhancing Large Language Models with Long-Term Memory
Wanjun Zhong, Lianghong Guo, Qiqi Gao +2
cs.CLcs.AIarXiv:2305.10250v32023
Online Adaptation of Language Models with a Memory of Amortized Contexts
Jihoon Tack, Jaehyung Kim, Eric Mitchell +3
cs.LGcs.CLarXiv:2403.04317v22024
Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
Jannik Brinkmann, Chris Wendler, Christian Bartelt +1
cs.CLarXiv:2501.06346v22025
Large Language Models Hack Rewards, and Society
Wei Liu, Xinyi Mou, Hanqi Yan +2
cs.LGcs.AIcs.CLarXiv:2606.04075v22026
A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input
Mateusz Malinowski, Mario Fritz
cs.AIcs.CLcs.CVarXiv:1410.0210v42014
Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
Clara Na, Ian Magnusson, Ananya Harsh Jha +4
cs.CLcs.LGarXiv:2410.15661v12024
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
Zhoujun Cheng, Shibo Hao, Tianyang Liu +21
cs.LGcs.AIcs.CLarXiv:2506.14965v12025
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
Nicholas Meade, Elinor Poole-Dayan, Siva Reddy
cs.CLcs.LGarXiv:2110.08527v32021
Domain Control for Neural Machine Translation
Catherine Kobus, Josep Crego, Jean Senellart
cs.CLarXiv:1612.06140v22016
Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning
Jiaxuan Lu, Ziyu Kong, Yemin Wang +10
cs.AIcs.CLcs.MAarXiv:2601.07641v12026
AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval
Tianyu Wang, Tianjiao Wu
cs.IRcs.CLarXiv:2609.01456v12026
Exploring LLM-based Agents for Root Cause Analysis
Devjeet Roy, Xuchao Zhang, Rashi Bhave +4
cs.SEcs.CLcs.LGarXiv:2403.04123v12024
A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha +3
cs.AIcs.CLcs.HCarXiv:2402.07927v22024
Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
Maciej Chrabąszcz, Aleksander Szymczyk, Marcin Sendera +2
cs.CLcs.CRarXiv:2605.18549v12026
Dissecting a Social Botnet: Growth, Content and Influence in Twitter
Norah Abokhodair, Daisy Yoo, David W. McDonald
cs.CYcs.CLcs.SIarXiv:1604.03627v12016
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
Christian Buck, Jannis Bulian, Massimiliano Ciaramita +4
cs.CLcs.AIarXiv:1705.07830v32017
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Xin Cheng, Rui Tian, Wangding Zeng +18
cs.CLcs.AIarXiv:2601.07372v22026
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
Yang Jin, Zhicheng Sun, Kun Xu +10
cs.CVcs.CLarXiv:2402.03161v32024
Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information
Kawin Ethayarajh, Yejin Choi, Swabha Swayamdipta
cs.CLcs.AIcs.LGarXiv:2110.08420v32021
Open-Domain Question Answering Goes Conversational via Question Rewriting
Raviteja Anantha, Svitlana Vakulenko, Zhucheng Tu +3
cs.IRcs.CLarXiv:2010.04898v32020
VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation
Kangning Zhang, Yixing Li, Shuai Shao +9
cs.CVcs.CLarXiv:2607.28590v12026
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Xin Men, Mingyu Xu, Qingyu Zhang +5
cs.CLarXiv:2403.03853v32024
ToolQA: A Dataset for LLM Question Answering with External Tools
Yuchen Zhuang, Yue Yu, Kuan Wang +2
cs.CLcs.AIarXiv:2306.13304v12023
Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective
Jaehyeon Kim, Suhwan Kim, Nakyung Lee +4
cs.CLcs.AIarXiv:2609.04489v12026
Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity
Terry Yue Zhuo, Yujin Huang, Chunyang Chen +1
cs.CLcs.SEarXiv:2301.12867v42023
Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection
Zhiwei Liu, Yupen Cao, Yuechen Jiang +22
cs.CLarXiv:2601.05403v22026
Do LLMs write like humans? Variation in grammatical and rhetorical styles
Alex Reinhart, Ben Markey, Michael Laudenbach +4
cs.CLarXiv:2410.16107v22024
Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling Curves
Sohail, Sarkar, Shakuntala Baichoo
cs.LGcs.CLmath.STarXiv:2609.40190v12026
A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation
Dipankar Sarkar
cs.CRcs.AIcs.CLarXiv:2608.14329v12026
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
Qitong Wang, Xinwei Niu, Mingluo Su +3
cs.LGcs.CLarXiv:2610.12327v12026
CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing
Huu Huy Nguyen, Chien Van Nguyen, Franck Dernoncourt +4
cs.LGcs.CLarXiv:2609.01925v12026

Computation and Language

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

Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning

Evaluating Factuality in Generation with Dependency-level Entailment

Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?

Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Tasks

A Comparative Study on End-to-end Speech to Text Translation

Improving the Accuracy of Pre-trained Word Embeddings for Sentiment Analysis

LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals

Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game

Towards General Agentic Intelligence via Environment Scaling

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis

GRIFFIN: Effective Token Alignment for Faster Speculative Decoding

OCNLI: Original Chinese Natural Language Inference

CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search

Identifying beneficial task relations for multi-task learning in deep neural networks

TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents

LocAgent: Graph-Guided LLM Agents for Code Localization

Yi: Open Foundation Models by 01.AI

Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems

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

Large Language Model Reasoning Failures

Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes

Answering Complex Open-domain Questions Through Iterative Query Generation

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Politeness Transfer: A Tag and Generate Approach

Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples

Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning

A Survey of Multimodal Retrieval-Augmented Generation

MemoryBank: Enhancing Large Language Models with Long-Term Memory

Online Adaptation of Language Models with a Memory of Amortized Contexts

Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages

Large Language Models Hack Rewards, and Society

A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input

Scalable Data Ablation Approximations for Language Models through Modular Training and Merging

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models

Domain Control for Neural Machine Translation

Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning

AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval

Exploring LLM-based Agents for Root Cause Analysis

A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics

Dissecting a Social Botnet: Growth, Content and Influence in Twitter

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information

Open-Domain Question Answering Goes Conversational via Question Rewriting

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

ToolQA: A Dataset for LLM Question Answering with External Tools

Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective

Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection

Do LLMs write like humans? Variation in grammatical and rhetorical styles

Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling Curves

A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation

SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference

CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing