大模型推理能力

Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models

Yuheng Wu, Wentao Guo, Zirui Liu, Heng Ji, Zhaozhuo Xu, Denghui Zhang

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

MetaSC: Test-Time Safety Specification Optimization for Language Models

Víctor Gallego

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

Comments Published at ICLR 2025 Workshop on Foundation Models in the Wild

Journal ref ICLR 2025 Workshop on Foundation Models in the Wild

Contradiction Detection in RAG Systems: Evaluating LLMs as Context Validators for Improved Information Consistency

Vignesh Gokul, Srikanth Tenneti, Alwarappan Nakkiran

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

Sabiá-3 Technical Report

Hugo Abonizio, Thales Sales Almeida, Thiago Laitz, Roseval Malaquias Junior, Giovana Kerche Bonás, Rodrigo Nogueira, Ramon Pires

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

Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning

Abdullah Vanlioglu

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

Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models

Haochen Liu, Song Wang, Chen Chen, Jundong Li

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

An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering

Alexander Murphy, Mohd Sanad Zaki Rizvi, Aden Haussmann, Ping Nie, Guifu Liu, Aryo Pradipta Gema, Pasquale Minervini

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

A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference

Giovanni Briglia, Stefano Mariani, Franco Zambonelli

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

Deterministic AI Agent Personality Expression through Standard Psychological Diagnostics

J. M. Diederik Kruijssen, Nicholas Emmons

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

Comments 25 pages, 8 figures, 4 tables; appeared in ADI (March 2025)

Journal ref ADI 2, 15-39 (2025)

Large Language Models and Causal Inference in Collaboration: A Survey

Xiaoyu Liu, Paiheng Xu, Junda Wu, Jiaxin Yuan, Yifan Yang, Yuhang Zhou, Fuxiao Liu, Tianrui Guan, Haoliang Wang, Tong Yu, Julian McAuley, Wei Ai, Furong Huang

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

Comments Findings of the Association for Computational Linguistics: NAACL 2025

MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration

David Wan, Justin Chih-Yao Chen, Elias Stengel-Eskin, Mohit Bansal

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

Comments NAACL 2025, 18 pages. Code: https://github.com/meetdavidwan/mammrefine

Gricean Norms as a Basis for Effective Collaboration

Fardin Saad, Pradeep K. Murukannaiah, Munindar P. Singh

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

Comments Accepted to AAMAS 2025. 8 pages (excl. references), 9 figures/tables. (Appendix: 5 pages, 6 figures/tables). Code available at: https://github.com/fardinsaad/Gricean-Norms

Opportunities for Large Language Models and Discourse in Engineering Design

Jan Göpfert, Jann M. Weinand, Patrick Kuckertz, Detlef Stolten

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

Combining Causal Models for More Accurate Abstractions of Neural Networks

Theodora-Mara Pîslar, Sara Magliacane, Atticus Geiger

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

Reinforcement Learning is all You Need

Yongsheng Lian

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

Comments 15 pages, 2 figures

AI-native Memory 2.0: Second Me

Jiale Wei, Xiang Ying, Tao Gao, Fangyi Bao, Felix Tao, Jingbo Shang

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

Cross-modal Causal Relation Alignment for Video Question Grounding

Weixing Chen, Yang Liu, Binglin Chen, Jiandong Su, Yongsen Zheng, Liang Lin

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

Comments Accepted by CVPR 2025

SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc

Daniel Guzman-Olivares, Lara Quijano-Sanchez, Federico Liberatore

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

Comments 15 pages, 2 figures, 7 tables, NAACL 2025

Towards Anthropomorphic Conversational AI Part I: A Practical Framework

Fei Wei, Yaliang Li, Bolin Ding

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

MV-CLAM: Multi-View Molecular Interpretation with Cross-Modal Projection via Language Model

Sumin Ha, Jun Hyeong Kim, Yinhua Piao, Sun Kim

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

Gated Delta Networks: Improving Mamba2 with Delta Rule

Songlin Yang, Jan Kautz, Ali Hatamizadeh

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

Comments ICLR 2025 camera ready

BEYONDWORDS is All You Need: Agentic Generative AI based Social Media Themes Extractor

Mohammed-Khalil Ghali, Abdelrahman Farrag, Sarah Lam, Daehan Won

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

Do GFlowNets Transfer? Case Study on the Game of 24/42

Adesh Gupta, Abhinav Kumar, Mansi Gupta, Paras Chopra

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

Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Mufei Li, Siqi Miao, Pan Li

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

Comments Accepted by ICLR 2025; Code available at https://github.com/Graph-COM/SubgraphRAG

LADs: Leveraging LLMs for AI-Driven DevOps

Ahmad Faraz Khan, Azal Ahmad Khan, Anas Mohamed, Haider Ali, Suchithra Moolinti, Sabaat Haroon, Usman Tahir, Mattia Fazzini, Ali R. Butt, Ali Anwar

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

Comments 17 pages with Appendix, 8 figures, and 7 tables. This paper is currently Under Review

Small Models are LLM Knowledge Triggers on Medical Tabular Prediction

Jiahuan Yan, Jintai Chen, Chaowen Hu, Bo Zheng, Yaojun Hu, Jimeng Sun, Jian Wu

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

Comments Accepted to ICLR 2025. Codes will be available at https://github.com/jyansir/sersal

SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning

Zexiong Ma, Chao Peng, Pengfei Gao, Xiangxin Meng, Yanzhen Zou, Bing Xie

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

Deterministic or probabilistic? The psychology of LLMs as random number generators

Javier Coronado-Blázquez

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

Comments 31 pages, 12 figures

GenAI vs. Human Fact-Checkers: Accurate Ratings, Flawed Rationales

Yuehong Cassandra Tai, Khushi Navin Patni, Nicholas Daniel Hemauer, Bruce Desmarais, Yu-Ru Lin

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

Comments Accepted for publication in the 17th ACM Web Science Conference 2025

Do Language Models Understand Time?

Xi Ding, Lei Wang

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

Comments Accepted for publication in the Companion Proceedings of the ACM Web Conference (WWW Companion 2025)