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)

14,101 to 14,160 of 19,296

SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ
Huy Hoang Le, Long-Bao Nguyen, Minh Tri Dao
cs.CLcs.SDarXiv:2609.11355v12026
Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing
Remo Grillo, Lukas Klic, Giovanni Colavizza
cs.AIcs.CLarXiv:2610.08095v12026
SkillFlow: Scalable and Efficient Agent Skill Retrieval System
Fangzhou Li, Pagkratios Tagkopoulos, Ilias Tagkopoulos
cs.AIcs.CLcs.MAarXiv:2504.06188v22025
Fully Hyperbolic Neural Networks
Weize Chen, Xu Han, Yankai Lin +5
cs.CLcs.LGarXiv:2105.14686v32021
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Yanghao Li, Rui Qian, Bowen Pan +24
cs.CVcs.CLcs.LGarXiv:2509.16197v12025
Building Social World Models with Large Language Models
Haofei Yu, Yining Zhao, Guanyu Lin +1
cs.SIcs.CLarXiv:2606.11482v12026
Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs
Mario Sanz-Guerrero, Minh Duc Bui, Katharina von der Wense
cs.CLarXiv:2509.15020v12025
Steering Llama 2 via Contrastive Activation Addition
Nina Panickssery, Nick Gabrieli, Julian Schulz +3
cs.CLcs.AIcs.LGarXiv:2312.06681v42023
Rethinking the Trust Region in LLM Reinforcement Learning
Penghui Qi, Xiangxin Zhou, Zichen Liu +4
cs.LGcs.AIcs.CLarXiv:2602.04879v32026
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering
Yingdong Shi, Ruiming Zhang, Changming Li +4
cs.CLarXiv:2605.30076v12026
Deploying Lifelong Open-Domain Dialogue Learning
Kurt Shuster, Jack Urbanek, Emily Dinan +2
cs.AIcs.CLarXiv:2008.08076v22020
CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data
Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett +94
cs.CLarXiv:2601.18026v22026
Overthinking Loops in Agents: A Structural Risk via MCP Tools
Yohan Lee, Jisoo Jang, Seoyeon Choi +2
cs.CLcs.CRarXiv:2602.14798v12026
Evaluating Large Language Models for Cross-Lingual Retrieval
Longfei Zuo, Pingjun Hong, Oliver Kraus +2
cs.CLcs.IRarXiv:2509.14749v12025
AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking
Dongxin Guo, Jikun Wu, Siu Ming Yiu
cs.SEcs.CLarXiv:2604.23581v12026
DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
Xirui Li, Ruochen Wang, Minhao Cheng +2
cs.CRcs.AIcs.CLarXiv:2402.16914v32024
Omni-IO Skills: Harnessing Your Agent Omni-Native
Yanlin Li, Mingyang Hao, Shengqiong Wu +3
cs.CLarXiv:2609.31847v12026
Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems
Andrea Madotto, Zihan Liu, Zhaojiang Lin +1
cs.CLcs.LGarXiv:2008.06239v22020
NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
Gengze Zhou, Yicong Hong, Jiazhao Zhang +9
cs.ROcs.AIcs.CLarXiv:2610.10787v12026
Improving Context Fidelity via Native Retrieval-Augmented Reasoning
Suyuchen Wang, Jinlin Wang, Xinyu Wang +6
cs.CLcs.AIarXiv:2509.13683v12025
Pre-trained Language Models in Biomedical Domain: A Systematic Survey
Benyou Wang, Qianqian Xie, Jiahuan Pei +4
cs.CLarXiv:2110.05006v42021
LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources
Haoyu Wang, Yujia Fu, Zhu Zhang +8
cs.CLarXiv:2504.05732v22025
Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
Tianbao Xie, Jiaqi Deng, Xiaochuan Li +12
cs.AIcs.CLcs.CVarXiv:2505.13227v32025
FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs
Md Mubtasim Ahasan, Rafat Hasan Khan, Tasnim Mohiuddin +6
cs.SDcs.AIcs.CLarXiv:2509.11425v22025
The Embedder's Dilemma: LLMs Are Better, but at What Cost?
Adnan El Assadi, Niklas Muennighoff, Jinhyuk Lee
cs.CLarXiv:2608.12875v12026
Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing
Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie +5
cs.CLarXiv:2209.14899v12022
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Chen Chen, Lai Wei
cs.LGcs.CLarXiv:2601.19895v22026
Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
Michael Hassid, Gabriel Synnaeve, Yossi Adi +1
cs.CLcs.AIarXiv:2505.17813v22025
HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR
Takanori Ashihara, Kohei Matsuura, Masato Mimura
eess.AScs.CLarXiv:2610.08063v12026
AgentRefine: Enhancing Agent Generalization through Refinement Tuning
Dayuan Fu, Keqing He, Yejie Wang +7
cs.AIcs.CLcs.ROarXiv:2501.01702v22025
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
Qiushi Sun, Kanzhi Cheng, Zichen Ding +12
cs.AIcs.CLcs.CVarXiv:2412.19723v32024
ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering
Ahmed Masry, Mohammed Saidul Islam, Mahir Ahmed +11
cs.CLarXiv:2504.05506v22025
Pseudowords as probes: Large Language Models show little of the sublexical sensitivity that governs human pseudoword processing
Jing Chen, Giulia Loca, Simona Amenta +1
cs.CLarXiv:2610.07936v12026
Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs
Ziqian Zhong, Aditi Raghunathan
cs.LGcs.CLarXiv:2508.00161v32025
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Kevin Qinghong Lin, Batu EI, Yuhong Shi +3
cs.CVcs.CLcs.CYarXiv:2606.11176v12026
How Output Format Confounds Data Quality and Capability in Instruction Tuning
Chengguang Gan, Hanjun Wei, Yunhao Liang +3
cs.CLarXiv:2609.02015v12026
Perturbation Sensitivity Analysis to Detect Unintended Model Biases
Vinodkumar Prabhakaran, Ben Hutchinson, Margaret Mitchell
cs.CLarXiv:1910.04210v12019
On Verbalized Confidence Scores for LLMs
Daniel Yang, Yao-Hung Hubert Tsai, Makoto Yamada
cs.CLarXiv:2412.14737v22024
On the Role of Citations in Preference Data
Yu Hou, Hal Daumé, Rachel Rudinger +1
cs.CLcs.AIarXiv:2608.21376v12026
SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation
Iman Barati, Mostafa Amiri, Heshaam Faili
cs.CLarXiv:2509.10708v12025
Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation
Chenghao Zhang, Guanting Dong, Yufan Liu +3
cs.CLcs.AIarXiv:2605.29861v22026
TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis
Xinran Li, Xinze Che, Yifan Lyu +2
cs.CLcs.AIarXiv:2605.01717v22026
On the Practical Computational Power of Finite Precision RNNs for Language Recognition
Gail Weiss, Yoav Goldberg, Eran Yahav
cs.LGcs.CLstat.MLarXiv:1805.04908v12018
LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale
Francesco Mantegna, Dulhan Jayalath, Gereon Elvers +12
cs.LGcs.CLarXiv:2608.25204v12026
ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs
Junyi Gao, Yu Shi, Pingzhao Hu +1
cs.CLcs.AIarXiv:2609.31448v12026
Agent-SafetyBench: Evaluating the Safety of LLM Agents
Zhexin Zhang, Shiyao Cui, Yida Lu +4
cs.CLarXiv:2412.14470v22024
Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation
Atta Ul Asad, Ahsan Bilal, Muhammad Ali +2
cs.CLarXiv:2608.30996v12026
OMIT the Action: Measuring Framing-Invariant Omission Bias under Philosophical Disagreement
Sihyeon Lee, Jihun Song, Chanwoo Kim +2
cs.CLarXiv:2610.07847v12026
BadPrompt: Backdoor Attacks on Continuous Prompts
Xiangrui Cai, Haidong Xu, Sihan Xu +2
cs.CLcs.AIarXiv:2211.14719v12022
Why Language Models Hallucinate
Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala +1
cs.CLarXiv:2509.04664v12025
Prompt-Learning for Fine-Grained Entity Typing
Ning Ding, Yulin Chen, Xu Han +6
cs.CLcs.AIarXiv:2108.10604v12021
Domain and Function: A Dual-Space Model of Semantic Relations and Compositions
Peter D. Turney
cs.CLcs.AIcs.LGarXiv:1309.4035v12013
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
Xinyuan Wang, Chenxi Li, Zhen Wang +6
cs.CLarXiv:2310.16427v22023
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
Jianuo Huang, Yaojie Zhang, Qituan Zhang +3
cs.CLarXiv:2605.29707v12026
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
Dongchan Min, Dong Bok Lee, Eunho Yang +1
eess.AScs.CLcs.LGarXiv:2106.03153v32021
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
Zhenni Bi, Kai Han, Chuanjian Liu +2
cs.CLcs.AIarXiv:2412.09078v52024
OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists
Chenyang Shao, Dehao Huang, Yu Li +18
cs.CYcs.CEcs.CLarXiv:2511.16931v22025
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
Andy Zhou, Bo Li, Haohan Wang
cs.LGcs.AIcs.CLarXiv:2401.17263v52024
Reward Hacking Challenges Oversight of Autonomous Research Agents
Yue Huang, Zhangchen Xu, Yuchen Ma +12
cs.CLcs.LGarXiv:2609.28614v12026
HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants
Benjamin Sturgeon, Daniel Samuelson, Jacob Haimes +1
cs.CYcs.AIcs.CLarXiv:2509.08494v22025

Computation and Language

SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ

Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing

SkillFlow: Scalable and Efficient Agent Skill Retrieval System

Fully Hyperbolic Neural Networks

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Building Social World Models with Large Language Models

Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs

Steering Llama 2 via Contrastive Activation Addition

Rethinking the Trust Region in LLM Reinforcement Learning

UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering

Deploying Lifelong Open-Domain Dialogue Learning

CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data

Overthinking Loops in Agents: A Structural Risk via MCP Tools

Evaluating Large Language Models for Cross-Lingual Retrieval

AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

Omni-IO Skills: Harnessing Your Agent Omni-Native

Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems

NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime

Improving Context Fidelity via Native Retrieval-Augmented Reasoning

Pre-trained Language Models in Biomedical Domain: A Systematic Survey

LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis

FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning

HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR

AgentRefine: Enhancing Agent Generalization through Refinement Tuning

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering

Pseudowords as probes: Large Language Models show little of the sublexical sensitivity that governs human pseudoword processing

Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs

Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories

How Output Format Confounds Data Quality and Capability in Instruction Tuning

Perturbation Sensitivity Analysis to Detect Unintended Model Biases

On Verbalized Confidence Scores for LLMs

On the Role of Citations in Preference Data

SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation

TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis

On the Practical Computational Power of Finite Precision RNNs for Language Recognition

LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale

ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs

Agent-SafetyBench: Evaluating the Safety of LLM Agents

Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation

OMIT the Action: Measuring Framing-Invariant Omission Bias under Philosophical Disagreement

BadPrompt: Backdoor Attacks on Continuous Prompts

Why Language Models Hallucinate

Prompt-Learning for Fine-Grained Entity Typing

Domain and Function: A Dual-Space Model of Semantic Relations and Compositions

PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning

OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

Reward Hacking Challenges Oversight of Autonomous Research Agents

HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants