大模型推理能力

Command-V: Pasting LLM Behaviors via Activation Profiles

Barry Wang, Avi Schwarzschild, Alexander Robey, Ali Payani, Charles Fleming, Mingjie Sun, Daphne Ippolito

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.LG

Truncated Proximal Policy Optimization

Tiantian Fan, Lingjun Liu, Yu Yue, Jiaze Chen, Chengyi Wang, Qiying Yu, Chi Zhang, Zhiqi Lin, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Bole Ma, Mofan Zhang, Gaohong Liu, Ru Zhang, Haotian Zhou, Cong Xie, Ruidong Zhu, Zhi Zhang, Xin Liu, Mingxuan Wang, Lin Yan, Yonghui Wu

机构 * ByteDance Seed（字节跳动种子） 纠错

专题命中 其他推理 ：reasoning(abstract)；CoT(abstract)；分类 cs.AI

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Zhepei Wei, Wei-Lin Chen, Xinyu Zhu, Yu Meng

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments ICML 2025. Code: https://github.com/weizhepei/AdaDecode

Non-literal Understanding of Number Words by Language Models

Polina Tsvilodub, Kanishk Gandhi, Haoran Zhao, Jan-Philipp Fränken, Michael Franke, Noah D. Goodman

机构 * Department of Linguistics, University of Tübingen（语言学系，图宾根大学） ； Department of Computer Science, Stanford University（计算机科学系，斯坦福大学） ； University of Washington（华盛顿大学） ； Department of Psychology, Stanford University（心理学系，斯坦福大学） ； Departments of Psychology & Computer Science, Stanford University（心理学与计算机科学系，斯坦福大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments 12 pages, 10 figures. To appear in the Proceedings of CogSci 2025

SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior

Jing-Jing Li, Valentina Pyatkin, Max Kleiman-Weiner, Liwei Jiang, Nouha Dziri, Anne G. E. Collins, Jana Schaich Borg, Maarten Sap, Yejin Choi, Sydney Levine

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments Accepted to ICML 2025

Improving Language Model Personas via Rationalization with Psychological Scaffolds

Brihi Joshi, Xiang Ren, Swabha Swayamdipta, Rik Koncel-Kedziorski, Tim Paek

机构 * University of Southern California（南加州大学） ； Apple（苹果公司） 纠错

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

LangPert: Detecting and Handling Task-level Perturbations for Robust Object Rearrangement

Xu Yin, Min-Sung Yoon, Yuchi Huo, Kang Zhang, Sung-Eui Yoon

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

On Language Models' Sensitivity to Suspicious Coincidences

Sriram Padmanabhan, Kanishka Misra, Kyle Mahowald, Eunsol Choi

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation

Qiyao Xue, Xiangyu Yin, Boyuan Yang, Wei Gao

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

Comments 28 pages

Journal ref in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Do Multimodal Large Language Models Understand Welding?

Grigorii Khvatskii, Yong Suk Lee, Corey Angst, Maria Gibbs, Robert Landers, Nitesh V. Chawla

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments 16 pages

Psy-Copilot: Visual Chain of Thought for Counseling

Keqi Chen, Zekai Sun, Huijun Lian, Yingming Gao, Ya Li

专题命中 其他推理 ：reasoning(abstract)；CoT(abstract)；分类 cs.CL

WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models

Yifu Chen, Shengpeng Ji, Haoxiao Wang, Ziqing Wang, Siyu Chen, Jinzheng He, Jin Xu, Zhou Zhao

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

Reflections on "Can AI Understand Our Universe?"

Yu Wang

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

Comments Invited talk at the 17th Marcel Grossmann Meeting, associated with arXiv:2404.10019, to be published in the International Journal of Modern Physics D

Leveraging Chain of Thought towards Empathetic Spoken Dialogue without Corresponding Question-Answering Data

Jingran Xie, Shun Lei, Yue Yu, Yang Xiang, Hui Wang, Xixin Wu, Zhiyong Wu

专题命中 其他推理 ：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL

Comments Accepted by ICASSP 2025

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Yilei Jiang, Yingshui Tan, Xiangyu Yue

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Lost in the Middle, and In-Between: Enhancing Language Models' Ability to Reason Over Long Contexts in Multi-Hop QA

George Arthur Baker, Ankush Raut, Sagi Shaier, Lawrence E Hunter, Katharina von der Wense

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

LLMDFA: Analyzing Dataflow in Code with Large Language Models

Chengpeng Wang, Wuqi Zhang, Zian Su, Xiangzhe Xu, Xiaoheng Xie, Xiangyu Zhang

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.LG

Comments 26 pages, 15 figures, 6 tables, NeurIPS 2024 poster

Towards Evaluating Large Language Models for Graph Query Generation

Siraj Munir, Alessandro Aldini

专题命中 其他推理 ：reasoning(abstract)；CoT(abstract)；分类 cs.CL

Comments Paper accepted and will be presented at CSCI2024 in December 2024, Later will be published at Springer LNCS

Enhancing Adversarial Attacks through Chain of Thought

Jingbo Su

专题命中 其他推理 ：reasoning(abstract)；CoT(abstract)；分类 cs.CL

SandboxAQ's submission to MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrieval

Isidora Chara Tourni, Sayontan Ghosh, Brenda Miao, Constantijn van der Poel

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments MRL 2024 Shared Task on Multi-lingual Multi-task Information Retrieval; 4th Multilingual Representation Learning (MRL) Workshop; EMNLP 2024

Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles

Xiao Pu, Tianxing He, Xiaojun Wan

专题命中 其他推理 ：reasoning(abstract)；CoT(abstract)；分类 cs.CL

Comments EMNLP 2024 Findings

Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish

Juan Manuel Pérez, Paula Miguel, Viviana Cotik

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

The Role of Governments in Increasing Interconnected Post-Deployment Monitoring of AI

Merlin Stein, Jamie Bernardi, Connor Dunlop

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI

Comments 7 pages, 2 figures, 1 table

Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models

Rui Meng, Ye Liu, Lifu Tu, Daqing He, Yingbo Zhou, Semih Yavuz

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments EMNLP 2024

Does Instruction Tuning Make LLMs More Consistent?

Constanza Fierro, Jiaang Li, Anders Søgaard

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments We need to run extra experiments to ensure some of the claims in the paper are fully correct

Leveraging Language Models for Emotion and Behavior Analysis in Education

Kaito Tanaka, Benjamin Tan, Brian Wong

专题命中 其他推理 ：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL

Comments 8 pages

Training Task Experts through Retrieval Based Distillation

Jiaxin Ge, Xueying Jia, Vijay Viswanathan, Hongyin Luo, Graham Neubig

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Universal Length Generalization with Turing Programs

Kaiying Hou, David Brandfonbrener, Sham Kakade, Samy Jelassi, Eran Malach

专题命中 其他推理 ：chain-of-thought(abstract)；CoT(abstract)；分类 cs.LG

Why Can Large Language Models Generate Correct Chain-of-Thoughts?

Rasul Tutunov, Antoine Grosnit, Juliusz Ziomek, Jun Wang, Haitham Bou-Ammar

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models

Tianjie Ju, Yijin Chen, Xinwei Yuan, Zhuosheng Zhang, Wei Du, Yubin Zheng, Gongshen Liu

专题命中 其他推理 ：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments Accepted at ACL 2024 (Long Paper. Main Conference)