大模型推理能力 - arXivDaily 专题

2502.15603 2025-02-24 cs.CL cs.AI cs.LG 67%

Do Multilingual LLMs Think In English?

Lisa Schut, Yarin Gal, Sebastian Farquhar

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Main paper 9 pages; including appendix 48 pages

2502.14255 2025-02-21 cs.CL cs.AI cs.ET cs.LG 67%

Effects of Prompt Length on Domain-specific Tasks for Large Language Models

Qibang Liu, Wenzhe Wang, Jeffrey Willard

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2405.16406 2025-02-21 cs.LG cs.AI cs.CL cs.CV 67%

SpinQuant: LLM quantization with learned rotations

Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, Tijmen Blankevoort

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICLR 2025

2502.07292 2025-02-12 cs.HC 67%

Investigating Creativity in Humans and Generative AI Through Circles Exercises

Runlin Duan, Shao-Kang Hsia, Yuzhao Chen, Yichen Hu, Ming Yin, Karthik Ramani

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)

2411.16646 2025-02-11 cs.CL cs.AI cs.LG 67%

Self-Generated Critiques Boost Reward Modeling for Language Models

Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to NAACL 2025 (Main Conference)

Journal ref NAACL 2025

2405.15973 2025-02-11 cs.CV cs.AI cs.CL cs.LG 67%

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement

Xiyao Wang, Jiuhai Chen, Zhaoyang Wang, Yuhang Zhou, Yiyang Zhou, Huaxiu Yao, Tianyi Zhou, Tom Goldstein, Parminder Bhatia, Furong Huang, Cao Xiao

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NAACL 2025 Findings

2502.02040 2025-02-05 cs.CL cs.AI cs.LG 67%

M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference

Nikhil Bhendawade, Mahyar Najibi, Devang Naik, Irina Belousova

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2410.06331 2025-02-04 cs.CL cs.AI cs.LG 67%

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

Zhuoran Zhang, Yongxiang Li, Zijian Kan, Keyuan Cheng, Lijie Hu, Di Wang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 24 pages

2406.12433 2025-02-04 cs.IR 67%

LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations

Jingtong Gao, Bo Chen, Weiwen Liu, Xiangyang Li, Yichao Wang, Wanyu Wang, Huifeng Guo, Ruiming Tang, Xiangyu Zhao

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)

2501.17186 2025-01-31 cs.AI cs.CL cs.LG 67%

Complete Chess Games Enable LLM Become A Chess Master

Yinqi Zhang, Xintian Han, Haolong Li, Kedi Chen, Shaohui Lin

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NAACL 2025

2501.17030 2025-01-29 cs.LG cs.AI cs.CL cs.CR 67%

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

Manojkumar Parmar, Yuvaraj Govindarajulu

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 9 pages, 1 table

2501.16784 2025-01-29 cs.CR 67%

TORCHLIGHT: Shedding LIGHT on Real-World Attacks on Cloudless IoT Devices Concealed within the Tor Network

Yumingzhi Pan, Zhen Ling, Yue Zhang, Hongze Wang, Guangchi Liu, Junzhou Luo, Xinwen Fu

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)

Comments 27 pages, 14 figure, 9 tables

2404.02127 2025-01-24 cs.CL cs.AI cs.LG 67%

LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain

Joel Niklaus, Lucia Zheng, Arya D. McCarthy, Christopher Hahn, Brian M. Rosen, Peter Henderson, Daniel E. Ho, Garrett Honke, Percy Liang, Christopher Manning

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at Findings of NAACL 2025

2501.03271 2025-01-22 cs.LG cs.AI cs.CL 67%

DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization

Amitava Das, Suranjana Trivedy, Danush Khanna, Rajarshi Roy, Gurpreet Singh, Basab Ghosh, Yaswanth Narsupalli, Vinija Jain, Vasu Sharma, Aishwarya Naresh Reganti, Aman Chadha

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2405.17969 2025-01-06 cs.CL cs.AI cs.CV cs.IR cs.LG 67%

Knowledge Circuits in Pretrained Transformers

Yunzhi Yao, Ningyu Zhang, Zekun Xi, Mengru Wang, Ziwen Xu, Shumin Deng, Huajun Chen

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NeurIPS 2024, 26 pages

2412.20725 2024-12-31 cs.CV 67%

Dialogue Director: Bridging the Gap in Dialogue Visualization for Multimodal Storytelling

Min Zhang, Zilin Wang, Liyan Chen, Kunhong Liu, Juncong Lin

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)

2411.04136 2024-12-31 cs.NI 67%

Large Language Models for Wireless Networks: An Overview from the Prompt Engineering Perspective

Hao Zhou, Chengming Hu, Dun Yuan, Ye Yuan, Di Wu, Xi Chen, Hina Tabassum, Xue Liu

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)

2411.03350 2024-12-31 cs.CL cs.AI cs.LG 67%

A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness

Fali Wang, Zhiwei Zhang, Xianren Zhang, Zongyu Wu, Tzuhao Mo, Qiuhao Lu, Wanjing Wang, Rui Li, Junjie Xu, Xianfeng Tang, Qi He, Yao Ma, Ming Huang, Suhang Wang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 78 pages, 32 figures, 14 tables

2407.21792 2024-12-30 cs.LG cs.AI cs.CL cs.CY 67%

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

Richard Ren, Steven Basart, Adam Khoja, Alice Gatti, Long Phan, Xuwang Yin, Mantas Mazeika, Alexander Pan, Gabriel Mukobi, Ryan H. Kim, Stephen Fitz, Dan Hendrycks

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NeurIPS 2024

2412.15462 2024-12-23 cs.RO cs.AI cs.CL cs.HC cs.LG 67%

TalkWithMachines: Enhancing Human-Robot Interaction for Interpretable Industrial Robotics Through Large/Vision Language Models

Ammar N. Abbas, Csaba Beleznai

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments This paper has been accepted for publication in the proceedings of the 2024 Eighth IEEE International Conference on Robotic Computing (IRC)

2412.14093 2024-12-23 cs.AI cs.CL cs.LG 67%

Alignment faking in large language models

Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Sam Marks, Johannes Treutlein, Tim Belonax, Jack Chen, David Duvenaud, Akbir Khan, Julian Michael, Sören Mindermann, Ethan Perez, Linda Petrini, Jonathan Uesato, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Evan Hubinger

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2412.11077 2024-12-23 cs.CV 67%

Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval

Yuanmin Tang, Xiaoting Qin, Jue Zhang, Jing Yu, Gaopeng Gou, Gang Xiong, Qingwei Ling, Saravan Rajmohan, Dongmei Zhang, Qi Wu

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)

2408.12763 2024-12-23 cs.LG cs.AI cs.CL 67%

Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models

Jean Park, Kuk Jin Jang, Basam Alasaly, Sriharsha Mopidevi, Andrew Zolensky, Eric Eaton, Insup Lee, Kevin Johnson

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2411.04118 2024-11-21 cs.CL cs.AI cs.LG 67%

Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?

Daniel P. Jeong, Saurabh Garg, Zachary C. Lipton, Michael Oberst

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments This version was published at EMNLP 2024 Main Conference as a Long Paper (Oral). See the extended version (arXiv:2411.08870) for additional results on QA tasks based on clinical notes and evaluations in the supervised fine-tuning regime

2404.13082 2024-11-21 cs.CL cs.AI cs.LG 67%

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning

Xuechen Zhang, Zijian Huang, Ege Onur Taga, Carlee Joe-Wong, Samet Oymak, Jiasi Chen

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2402.02549 2024-11-14 cs.CL cs.AI cs.LG 67%

Are Large Language Models Table-based Fact-Checkers?

Hanwen Zhang, Qingyi Si, Peng Fu, Zheng Lin, Weiping Wang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments CSCWD 2024

2410.21480 2024-10-30 cs.LG cs.AI cs.CL cs.CV 67%

AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification

Brendan Hogan, Anmol Kabra, Felipe Siqueira Pacheco, Laura Greenstreet, Joshua Fan, Aaron Ferber, Marta Ummus, Alecsander Brito, Olivia Graham, Lillian Aoki, Drew Harvell, Alex Flecker, Carla Gomes

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2410.15570 2024-10-22 cs.CL cs.AI cs.LG 67%

Stacking Small Language Models for Generalizability

Laurence Liang

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2408.05874 2024-10-16 cs.CL cs.AI cs.LG 67%

LLM-Based Robust Product Classification in Commerce and Compliance

Sina Gholamian, Gianfranco Romani, Bartosz Rudnikowicz, Stavroula Skylaki

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Camera-ready version for Customizable NLP Workshop at EMNLP 2024. 11 pages

2410.06524 2024-10-10 cs.CL cs.AI cs.LG 67%

Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA

Maharshi Gor, Hal Daumé, Tianyi Zhou, Jordan Boyd-Graber

专题命中其他推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments To appear at EMNLP 2024 (Main)

1. 其他推理 5804 篇

Do Multilingual LLMs Think In English?

Effects of Prompt Length on Domain-specific Tasks for Large Language Models

SpinQuant: LLM quantization with learned rotations

Investigating Creativity in Humans and Generative AI Through Circles Exercises

Self-Generated Critiques Boost Reward Modeling for Language Models

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement

M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations

Complete Chess Games Enable LLM Become A Chess Master

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

TORCHLIGHT: Shedding LIGHT on Real-World Attacks on Cloudless IoT Devices Concealed within the Tor Network

LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain

DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization

Knowledge Circuits in Pretrained Transformers

Dialogue Director: Bridging the Gap in Dialogue Visualization for Multimodal Storytelling

Large Language Models for Wireless Networks: An Overview from the Prompt Engineering Perspective

A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

TalkWithMachines: Enhancing Human-Robot Interaction for Interpretable Industrial Robotics Through Large/Vision Language Models

Alignment faking in large language models

Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval

Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models

Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning

Are Large Language Models Table-based Fact-Checkers?

AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification

Stacking Small Language Models for Generalizability

LLM-Based Robust Product Classification in Commerce and Compliance

Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA