大模型推理能力

Superalignment with Dynamic Human Values

Florian Mai, David Kaczér, Nicholas Kluge Corrêa, Lucie Flek

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Comments Published at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment (BiAlign)

TableBench: A Comprehensive and Complex Benchmark for Table Question Answering

Xianjie Wu, Jian Yang, Linzheng Chai, Ge Zhang, Jiaheng Liu, Xinrun Du, Di Liang, Daixin Shu, Xianfu Cheng, Tianzhen Sun, Guanglin Niu, Tongliang Li, Zhoujun Li

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Comments 12 pages

Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from Plots

Maciej P. Polak, Dane Morgan

专题命中 复杂问题求解 ：chain-of-thought(abstract)；分类 cs.AI

Comments 8 pages, 3 figures

Quantum Many-Body Physics Calculations with Large Language Models

Haining Pan, Nayantara Mudur, Will Taranto, Maria Tikhanovskaya, Subhashini Venugopalan, Yasaman Bahri, Michael P. Brenner, Eun-Ah Kim

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Comments 9 pages, 4 figures. Supplemental material in the source file

Journal ref Commun Phys 8, 49 (2025)

Associative Transformer

Yuwei Sun, Hideya Ochiai, Zhirong Wu, Stephen Lin, Ryota Kanai

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.LG

Comments Accepted for CVPR 2025

Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios

Chao Wang, Luning Zhang, Zheng Wang, Yang Zhou

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Comments 11pages

Perceptions of Sentient AI and Other Digital Minds: Evidence from the AI, Morality, and Sentience (AIMS) Survey

Jacy Reese Anthis, Janet V. T. Pauketat, Ali Ladak, Aikaterina Manoli

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Comments Published at CHI 2025

DETQUS: Decomposition-Enhanced Transformers for QUery-focused Summarization

Yasir Khan, Xinlei Wu, Sangpil Youm, Justin Ho, Aryaan Shaikh, Jairo Garciga, Rohan Sharma, Bonnie J. Dorr

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Comments 12 pages, 2 figures, Accepted to NAACL 2025 main conference

SYMBIOSIS: Systems Thinking and Machine Intelligence for Better Outcomes in Society

Sameer Sethi, Donald Martin, Emmanuel Klu

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs

Ruichen Zhang, Mufan Qiu, Zhen Tan, Mohan Zhang, Vincent Lu, Jie Peng, Kaidi Xu, Leandro Z. Agudelo, Peter Qian, Tianlong Chen

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.LG

DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models

YiQiu Guo, Yuchen Yang, Zhe Chen, Pingjie Wang, Yusheng Liao, Ya Zhang, Yanfeng Wang, Yu Wang

专题命中 复杂问题求解 ：self-correction(abstract)；分类 cs.CL

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

Mingyang Chen, Haoze Sun, Tianpeng Li, Fan Yang, Hao Liang, Keer Lu, Bin Cui, Wentao Zhang, Zenan Zhou, Weipeng Chen

专题命中 复杂问题求解 ：planning(abstract)；分类 cs.CL

Comments Accepted to ICLR 2025

KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA

Xiaorui Su, Yibo Wang, Shanghua Gao, Xiaolong Liu, Valentina Giunchiglia, Djork-Arné Clevert, Marinka Zitnik

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Journal ref ICLR2025

Intelligence at the Edge of Chaos

Shiyang Zhang, Aakash Patel, Syed A Rizvi, Nianchen Liu, Sizhuang He, Amin Karbasi, Emanuele Zappala, David van Dijk

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Comments 15 pages,8 Figures

An LLM-based Delphi Study to Predict GenAI Evolution

Francesco Bertolotti, Luca Mari

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

HazardNet: A Small-Scale Vision Language Model for Real-Time Traffic Safety Detection at Edge Devices

Mohammad Abu Tami, Mohammed Elhenawy, Huthaifa I. Ashqar

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Explain the Black Box for the Sake of Science: the Scientific Method in the Era of Generative Artificial Intelligence

Gianmarco Mengaldo

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation

Humza Sami, Mubashir ul Islam, Samy Charas, Asav Gandhi, Pierre-Emmanuel Gaillardon, Valerio Tenace

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

BarkXAI: A Lightweight Post-Hoc Explainable Method for Tree Species Classification with Quantifiable Concepts

Yunmei Huang, Songlin Hou, Zachary Nelson Horve, Songlin Fei

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

MLPs Learn In-Context on Regression and Classification Tasks

William L. Tong, Cengiz Pehlevan

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.LG

Comments Published at ICLR 2025. 30 pages, 10 figures, code available at https://github.com/wtong98/mlp-icl

Beyond Pattern Recognition: Probing Mental Representations of LMs

Moritz Miller, Kumar Shridhar

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale

Jiaxi Li, Xingxing Zhang, Xun Wang, Xiaolong Huang, Li Dong, Liang Wang, Si-Qing Chen, Wei Lu, Furu Wei

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

A Fine-Tuning Approach for T5 Using Knowledge Graphs to Address Complex Tasks

Xiaoxuan Liao, Binrong Zhu, Jacky He, Guiran Liu, Hongye Zheng, Jia Gao

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking

Yilong Chen, Junyuan Shang, Zhenyu Zhang, Yanxi Xie, Jiawei Sheng, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Comments 15 pages, 11 figures

Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

Zhenyu Pan, Haozheng Luo, Manling Li, Han Liu

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Comments International Conference on Learning Representations (ICLR) 2025

Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection

Han Zhang, Langshi Zhou, Hanfang Yang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization

Zheyuan Zhang, Runze Li, Tasnim Kabir, Jordan Boyd-Graber

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Adapting Large Language Models for Time Series Modeling via a Novel Parameter-efficient Adaptation Method

Juyuan Zhang, Wei Zhu, Jiechao Gao

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading

Guojun Xiong, Zhiyang Deng, Keyi Wang, Yupeng Cao, Haohang Li, Yangyang Yu, Xueqing Peng, Mingquan Lin, Kaleb E Smith, Xiao-Yang Liu, Jimin Huang, Sophia Ananiadou, Qianqian Xie

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI

Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing

Xiaoju Ye, Zhichun Wang, Jingyuan Wang

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL

Comments 21 pages