大模型推理能力 - arXivDaily 专题

2411.05037 2024-11-11 cs.CL cs.AI cs.LG 82%

Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning

Mansi Sakarvadia

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

Comments University of Chicago, Computer Science, Master of Science Dissertation

2410.17050 2024-10-23 cs.LG cs.AI cs.CL 82%

UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs

Yash Sinha, Murari Mandal, Mohan Kankanhalli

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

2409.18996 2024-10-01 cs.CL cs.AI cs.CV cs.LG cs.MM 82%

From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models

Shengsheng Qian, Zuyi Zhou, Dizhan Xue, Bing Wang, Changsheng Xu

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

2405.11880 2024-05-21 cs.LG cs.AI cs.CL cs.CV 82%

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs

Siyu Lou, Yuntian Chen, Xiaodan Liang, Liang Lin, Quanshi Zhang

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

2404.10226 2024-04-17 cs.AI cs.CL cs.CV cs.LG 82%

Find The Gap: Knowledge Base Reasoning For Visual Question Answering

Elham J. Barezi, Parisa Kordjamshidi

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

2404.04525 2024-04-09 cs.CL cs.AI cs.LG 82%

IITK at SemEval-2024 Task 10: Who is the speaker? Improving Emotion Recognition and Flip Reasoning in Conversations via Speaker Embeddings

Shubham Patel, Divyaksh Shukla, Ashutosh Modi

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

Comments Accepted at SemEval 2024, NAACL 2024; 10 Pages

2404.02934 2024-04-05 cs.CL cs.AI cs.CY cs.LG 82%

GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning

Jeffy Yu, Maximilian Huber, Kevin Tang

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

Comments 9 pages, 1 figure

2403.15464 2024-03-26 cs.CL cs.AI cs.LG cs.MA 82%

LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction

Hejie Cui, Zhuocheng Shen, Jieyu Zhang, Hui Shao, Lianhui Qin, Joyce C. Ho, Carl Yang

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

2310.06117 2024-03-13 cs.LG cs.AI cs.CL 82%

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H. Chi, Quoc V Le, Denny Zhou

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

Comments ICLR 2024

2309.05605 2024-03-01 cs.CL cs.AI cs.LG 82%

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models

Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Daniel Grzenda, Nathaniel Hudson, André Bauer, Kyle Chard, Ian Foster

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

Comments Oral Presentation at BlackboxNLP Workshop at EMNLP 2023

2402.17230 2024-02-28 cs.CR 82%

Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities

Yu Nong, Mohammed Aldeen, Long Cheng, Hongxin Hu, Feng Chen, Haipeng Cai

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

2311.16173 2023-12-07 cs.AI cs.CL cs.LG 82%

Conditions for Length Generalization in Learning Reasoning Skills

Changnan Xiao, Bing Liu

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

2305.06349 2023-11-07 cs.CL cs.AI cs.LG 82%

RECKONING: Reasoning through Dynamic Knowledge Encoding

Zeming Chen, Gail Weiss, Eric Mitchell, Asli Celikyilmaz, Antoine Bosselut

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

Comments 22 pages, 8 figures, 10 tables, Accepted to NeurIPS 2023

2305.18395 2023-10-31 cs.CL cs.AI cs.LG 82%

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Minki Kang, Seanie Lee, Jinheon Baek, Kenji Kawaguchi, Sung Ju Hwang

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

Comments NeurIPS 2023

2306.02797 2023-10-02 cs.CL cs.AI cs.LG 82%

Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language

Kevin Ellis

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

Comments NeurIPS 2023 oral

2309.12485 2023-09-25 cs.CL cs.AI cs.LG 82%

Studying and improving reasoning in humans and machines

Nicolas Yax, Hernan Anlló, Stefano Palminteri

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

Comments The paper is split in 4 parts : main text (pages 2-27), methods (pages 28-34), technical appendix (pages 35-45) and supplementary methods (pages 46-125)

2305.14106 2023-05-24 cs.CL cs.AI cs.LG 82%

Better Zero-Shot Reasoning with Self-Adaptive Prompting

Xingchen Wan, Ruoxi Sun, Hanjun Dai, Sercan O. Arik, Tomas Pfister

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

Comments Findings of the Association for Computational Linguistics: ACL 2023. 10 pages, 2 tables, 4 figures (20 pages, 8 tables, 7 figures including references and appendices)

2212.09721 2023-05-23 cs.CL cs.AI cs.LG 82%

KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales

Aaron Chan, Zhiyuan Zeng, Wyatt Lake, Brihi Joshi, Hanjie Chen, Xiang Ren

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

Comments TrustML-(un)Limited Workshop at ICLR 2023

2209.08141 2023-05-23 cs.CL cs.AI cs.LG 82%

Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models

Ben Prystawski, Paul Thibodeau, Christopher Potts, Noah D. Goodman

专题命中其他推理：chain-of-thought(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 7 pages, 1 figure

2104.08793 2022-12-20 cs.CL cs.AI cs.LG 82%

SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning

Aaron Chan, Jiashu Xu, Boyuan Long, Soumya Sanyal, Tanishq Gupta, Xiang Ren

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

Comments NeurIPS 2021

2103.00820 2022-12-08 cs.AI cs.CL cs.CV cs.LG 82%

Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues

Hung Le, Nancy F. Chen, Steven C. H. Hoi

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

Comments Accepted at ICLR (International Conference on Learning Representations) 2021

2207.05155 2022-07-13 cs.AI cs.CL cs.LG 82%

Can Language Models perform Abductive Commonsense Reasoning?

Seungone Kim

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

Comments 6 pages

2206.14858 2022-07-04 cs.CL cs.AI cs.LG 82%

Solving Quantitative Reasoning Problems with Language Models

Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, Yuhuai Wu, Behnam Neyshabur, Guy Gur-Ari, Vedant Misra

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

Comments 12 pages, 5 figures + references and appendices

2202.00436 2022-06-20 cs.CL cs.AI cs.LG stat.AP 82%

ROCK: Causal Inference Principles for Reasoning about Commonsense Causality

Jiayao Zhang, Hongming Zhang, Weijie J. Su, Dan Roth

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

Comments To appear, ICML 2022

2102.07043 2021-06-16 cs.AI cs.CL cs.LG 82%

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

Haitian Sun, Pat Verga, Bhuwan Dhingra, Ruslan Salakhutdinov, William W. Cohen

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

Comments Accepted at the 38th International Conference on Machine Learning, PMLR 139, 2021

2003.03446 2020-03-10 cs.CL cs.AI cs.LG 82%

Natural Language QA Approaches using Reasoning with External Knowledge

Chitta Baral, Pratyay Banerjee, Kuntal Kumar Pal, Arindam Mitra

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

Comments 6 pages, 3 figures, Work in Progress

2606.00229 2026-06-09 cs.RO cs.AI cs.LG 版本更新 82%

Continuous Reasoning for Vision-Language-Action

视觉-语言-动作的连续推理

Yueh-Hua Wu, Tatsuya Matsushima, Kei Ota

机构 * Airoa

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

AI总结针对视觉-语言-动作策略中语言与连续控制粒度不匹配的问题，提出一种可共享、可验证的连续推理方法，通过高斯潜变量接口和自验证目标提升机器人任务成功率。

Comments Project page: https://continuous-reasoning.airoa.io

2509.20336 2025-09-25 cs.LG cs.AI 82%

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing

Xinnan Dai, Chung-Hsiang Lo, Kai Guo, Shenglai Zeng, Dongsheng Luo, Jiliang Tang

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

Comments Accepted by the Workshop on Efficient Reasoning, Neurips 2025

2409.06241 2025-07-15 cs.LG cs.AI 82%

DiPT: Enhancing LLM reasoning through diversified perspective-taking

Hoang Anh Just, Mahavir Dabas, Lifu Huang, Ming Jin, Ruoxi Jia

机构 * Virginia Tech（弗吉尼亚理工大学）； UC Davis（加州大学戴维斯分校）

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

Comments LLM Reasoning with Perspectives, NAACL 2025 Findings

2010.12237 2020-11-13 cs.AI cs.LG 82%

Algorithms for Causal Reasoning in Probability Trees

Tim Genewein, Tom McGrath, Grégoire Déletang, Vladimir Mikulik, Miljan Martic, Shane Legg, Pedro A. Ortega

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

Comments (2nd version with correction to algorithm) 11 pages, 8 figures, 5 algorithms. A companion Colaboratory tutorial is available at https://github.com/deepmind/deepmind-research/tree/master/causal_reasoning

1. 其他推理 5768 篇

Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning

UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs

From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs

Find The Gap: Knowledge Base Reasoning For Visual Question Answering

IITK at SemEval-2024 Task 10: Who is the speaker? Improving Emotion Recognition and Flip Reasoning in Conversations via Speaker Embeddings

GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning

LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models

Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities

Conditions for Length Generalization in Learning Reasoning Skills

RECKONING: Reasoning through Dynamic Knowledge Encoding

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language

Studying and improving reasoning in humans and machines

Better Zero-Shot Reasoning with Self-Adaptive Prompting

KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales

Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models

SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning

Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues

Can Language Models perform Abductive Commonsense Reasoning?

Solving Quantitative Reasoning Problems with Language Models

ROCK: Causal Inference Principles for Reasoning about Commonsense Causality

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

Natural Language QA Approaches using Reasoning with External Knowledge

Continuous Reasoning for Vision-Language-Action

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing

DiPT: Enhancing LLM reasoning through diversified perspective-taking

Algorithms for Causal Reasoning in Probability Trees