大模型推理能力 - arXivDaily 专题

2501.17507 2025-01-30 cs.AI astro-ph.HE astro-ph.IM 70%

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

2501.10937 2025-01-22 cs.CL cs.SD eess.AS 70%

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

2412.18826 2024-12-30 cs.CL 70%

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

2412.10079 2024-12-16 cs.CL 70%

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

2402.10754 2024-11-26 cs.PL cs.LG cs.SE 70%

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

2411.08449 2024-11-19 cs.ET cs.CL 70%

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

2410.21791 2024-10-30 cs.CL 70%

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

2410.21501 2024-10-30 cs.CL 70%

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

2410.14042 2024-10-21 cs.CL 70%

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

2410.12174 2024-10-17 cs.CL 70%

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

2410.04931 2024-10-08 cs.CY cs.AI cs.HC 70%

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

2410.02308 2024-10-04 cs.CL 70%

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

2404.15206 2024-10-04 cs.CL 70%

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

2408.06874 2024-08-14 cs.CL 70%

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

2407.05463 2024-07-09 cs.CL 70%

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

2407.03310 2024-07-04 cs.LG 70%

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

2310.13571 2024-06-07 cs.CL 70%

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

2402.11900 2024-06-04 cs.CL 70%

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)

2405.11040 2024-05-21 cs.CL physics.med-ph 70%

From Generalist to Specialist: Improving Large Language Models for Medical Physics Using ARCoT

Jace Grandinetti, Rafe McBeth

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

Comments 8 pages, 3 figures, 1 table

2310.14025 2024-04-23 cs.CL 70%

Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation

Anastasia Kritharoula, Maria Lymperaiou, Giorgos Stamou

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

Comments Conference on Empirical Methods in Natural Language Processing (EMNLP) 2023

Journal ref Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

2308.12574 2024-04-09 cs.IR cs.AI 70%

Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs

Ye Liu, Semih Yavuz, Rui Meng, Meghana Moorthy, Shafiq Joty, Caiming Xiong, Yingbo Zhou

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

2402.01727 2024-02-06 cs.CY cs.AI 70%

Prompting Diverse Ideas: Increasing AI Idea Variance

Lennart Meincke, Ethan R. Mollick, Christian Terwiesch

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

2310.14422 2024-02-02 cs.CL 70%

Large Language Models are biased to overestimate profoundness

Eugenio Herrera-Berg, Tomás Vergara Browne, Pablo León-Villagrá, Marc-Lluís Vives, Cristian Buc Calderon

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

Comments 5 pages, 3 figures

Journal ref https://aclanthology.org/2023.emnlp-main.599

2312.03458 2023-12-07 cs.CL 70%

Think from Words(TFW): Initiating Human-Like Cognition in Large Language Models Through Think from Words for Japanese Text-level Classification

Chengguang Gan, Qinghao Zhang, Tatsunori Mori

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

2312.01044 2023-12-05 cs.CL 70%

Large Language Models Are Zero-Shot Text Classifiers

Zhiqiang Wang, Yiran Pang, Yanbin Lin

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

Comments 9 pages, 3 figures, 6 tables

2205.05131 2023-03-01 cs.CL 70%

UL2: Unifying Language Learning Paradigms

Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Jason Wei, Xuezhi Wang, Hyung Won Chung, Siamak Shakeri, Dara Bahri, Tal Schuster, Huaixiu Steven Zheng, Denny Zhou, Neil Houlsby, Donald Metzler

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

Comments Updated Q1 2023 with Flan-UL2 20B release! :)

2510.21131 2025-10-27 cs.CL cs.AI cs.LG 69%

Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications

Guangxin Su, Hanchen Wang, Jianwei Wang, Wenjie Zhang, Ying Zhang, Jian Pei

机构 * The University of New South Wales（新南威尔士大学）； The University of Technology Sydney（技术大学悉尼分校）； University of Technology Sydney（技术大学悉尼分校）； Duke University（杜克大学）

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

Comments Surveys and overviews; Natural language processing; Knowledge representation and reasoning; Graph algorithms

2308.12219 2025-02-25 cs.CL cs.AI cs.LG 69%

Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning

Jiasheng Ye, Zaixiang Zheng, Yu Bao, Lihua Qian, Quanquan Gu

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

Comments add results on reasoning and multimodality; add discussions on latest progress

2608.23244 2026-08-25 cs.CL cs.AI cs.LG stat.ML 新提交 67%

Credal Large Language Models for Semantic Commitment under Uncertainty

用于不确定性下语义承诺的Credal大语言模型

Shireen Kudukkil Manchingal, Sofiia Nikolenko, Fabio Cuzzolin

机构 * Oxford Dynamics（牛津动力学）； Ludwig-Maximilians-Universität München（慕尼黑大学）； Institute for Artificial Intelligence, Data Analysis and Systems (AIDAS)（人工智能、数据分析与系统研究所）； School of Engineering Computing & Mathematics（工程计算与数学学院）； Oxford Brookes University（牛津布鲁克斯大学）

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

AI总结本研究提出Credal大语言模型（CLLMs），通过LoRA适配器集成体构建Credal集合，推导CTC和SCC两类承诺分数，在多模型多数据集上验证其在问答、幻觉检测等任务中表现优异。

Comments 31 pages, 5 figures, 13 tables

2608.19072 2026-08-20 cs.AI cs.CL cs.LG 新提交 67%

What is Missing from AI Post-Training AI: An Empirical Analysis

AI后训练AI缺失了什么？一项实证分析

Joy Jia Yin Lim, Xin Huang, Hao Peng, Yaxi Lu, Xin Cong, Zhong Zhang, Maosong Sun, Yankai Lin

机构 * Tsinghua University（清华大学）； University of Electronic Science and Technology of China（电子科技大学）； Renmin University of China（中国人民大学）

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

AI总结本文通过实证分析发现，LLM智能体后训练时存在策略锁定问题，其缺失的是执行过程中自发重新评估训练策略的机制，而非经验、指导或推理计算。

1. 其他推理 5849 篇

Reflections on "Can AI Understand Our Universe?"

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

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

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

LLMDFA: Analyzing Dataflow in Code with Large Language Models

Towards Evaluating Large Language Models for Graph Query Generation

Enhancing Adversarial Attacks through Chain of Thought

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

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

Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish

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

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

Does Instruction Tuning Make LLMs More Consistent?

Leveraging Language Models for Emotion and Behavior Analysis in Education

Training Task Experts through Retrieval Based Distillation

Universal Length Generalization with Turing Programs

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

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

From Generalist to Specialist: Improving Large Language Models for Medical Physics Using ARCoT

Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation

Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs

Prompting Diverse Ideas: Increasing AI Idea Variance

Large Language Models are biased to overestimate profoundness

Think from Words(TFW): Initiating Human-Like Cognition in Large Language Models Through Think from Words for Japanese Text-level Classification

Large Language Models Are Zero-Shot Text Classifiers

UL2: Unifying Language Learning Paradigms

Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications

Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning

Credal Large Language Models for Semantic Commitment under Uncertainty

What is Missing from AI Post-Training AI: An Empirical Analysis