大模型推理能力 - arXivDaily 专题

2504.13958 2025-04-22 cs.LG cs.AI cs.CL 67%

ToolRL: Reward is All Tool Learning Needs

Cheng Qian, Emre Can Acikgoz, Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments 19 Pages, 12 Figures, 12 Tables

2406.05821 2025-04-14 cs.CV 67%

F-LMM: Grounding Frozen Large Multimodal Models

Size Wu, Sheng Jin, Wenwei Zhang, Lumin Xu, Wentao Liu, Wei Li, Chen Change Loy

专题命中复杂问题求解：reasoning(abstract)；chain-of-thought(abstract)

Comments Project Page: https://github.com/wusize/F-LMM

2504.07097 2025-04-10 cs.LG cs.AI cs.CL math.PR stat.ML 67%

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning

Nikhil Shivakumar Nayak, Krishnateja Killamsetty, Ligong Han, Abhishek Bhandwaldar, Prateek Chanda, Kai Xu, Hao Wang, Aldo Pareja, Oleg Silkin, Mustafa Eyceoz, Akash Srivastava

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

Comments 25 pages, 13 figures, 6 tables

2503.05050 2025-04-09 cs.CL cs.AI cs.LG 67%

A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs

Melkamu Abay Mersha, Mesay Gemeda Yigezu, Hassan Shakil, Ali K. AlShami, Sanghyun Byun, Jugal Kalita

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

Comments arXiv admin note: substantial text overlap with arXiv:2501.15374

2504.04915 2025-04-08 cs.CL cs.AI cs.IR cs.LG 67%

Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration

Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu, Joyce C. Ho, Haoyu Wang, Carl Yang

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

Comments Work in progress. Code: https://github.com/ritaranx/Collab-RAG/

2504.00906 2025-04-02 cs.AI cs.CL cs.CV cs.LG 67%

Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

Saaket Agashe, Kyle Wong, Vincent Tu, Jiachen Yang, Ang Li, Xin Eric Wang

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

Comments 18 pages, 13 figures, 8 tables

2410.14052 2025-03-21 cs.CL cs.AI cs.LG 67%

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs

Alireza Rezazadeh, Zichao Li, Wei Wei, Yujia Bao

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

2408.15045 2025-03-20 cs.CV 67%

DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

Wenhui Liao, Jiapeng Wang, Hongliang Li, Chengyu Wang, Jun Huang, Lianwen Jin

专题命中复杂问题求解：chain-of-thought(abstract)；CoT(abstract)

Comments CVPR2025

2405.17418 2025-03-20 cs.CV 67%

A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation

Chenxuan Li, Jiaming Liu, Guanqun Wang, Xiaoqi Li, Sixiang Chen, Liang Heng, Chuyan Xiong, Jiaxin Ge, Renrui Zhang, Kaichen Zhou, Shanghang Zhang

专题命中复杂问题求解：reasoning(abstract)；chain-of-thought(abstract)

2501.15374 2025-03-14 cs.CL cs.AI cs.CY cs.LG 67%

Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models

Melkamu Abay Mersha, Mesay Gemeda Yigezu, Jugal Kalita

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

Journal ref 310(2025)113042

2501.02393 2025-03-06 cs.LG cond-mat.mes-hall cond-mat.mtrl-sci cs.AI cs.CL 67%

Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers

Markus J. Buehler

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

2412.06071 2025-03-03 cs.CL cs.AI cs.LG 67%

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

Fan Wang, Juyong Jiang, Chansung Park, Sunghun Kim, Jing Tang

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

Comments The first three authors contributed equally to this work; Accepted by ICLR 2025

2502.15964 2025-02-27 cs.LG cs.AI cs.CL cs.DC 67%

Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models

Avanika Narayan, Dan Biderman, Sabri Eyuboglu, Avner May, Scott Linderman, James Zou, Christopher Re

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

2502.13870 2025-02-20 cs.LG cs.AI cs.CL cs.IT math.IT 67%

SPEX: Scaling Feature Interaction Explanations for LLMs

Justin Singh Kang, Landon Butler, Abhineet Agarwal, Yigit Efe Erginbas, Ramtin Pedarsani, Kannan Ramchandran, Bin Yu

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

2502.13189 2025-02-20 cs.LG cs.AI cs.CL 67%

MoBA: Mixture of Block Attention for Long-Context LLMs

Enzhe Lu, Zhejun Jiang, Jingyuan Liu, Yulun Du, Tao Jiang, Chao Hong, Shaowei Liu, Weiran He, Enming Yuan, Yuzhi Wang, Zhiqi Huang, Huan Yuan, Suting Xu, Xinran Xu, Guokun Lai, Yanru Chen, Huabin Zheng, Junjie Yan, Jianlin Su, Yuxin Wu, Neo Y. Zhang, Zhilin Yang, Xinyu Zhou, Mingxing Zhang, Jiezhong Qiu

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

Comments 15 pages

2410.12480 2025-02-18 cs.CL cs.AI cs.DB cs.LG 67%

KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs

Yongqin Xu, Huan Li, Ke Chen, Lidan Shou

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

Comments under reveiw; new results and analysis added, typos corrected

2401.17809 2025-02-18 cs.CL cs.AI cs.LG 67%

SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering

Xiaopeng Li, Shasha Li, Shezheng Song, Huijun Liu, Bin Ji, Xi Wang, Jun Ma, Jie Yu, Xiaodong Liu, Jing Wang, Weimin Zhang

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

Comments AAAI25. Our code is available at https://github.com/xpq-tech/SWEA

2408.13986 2025-02-11 cs.LG cs.AI cs.CL cs.IR 67%

AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction

Jie Feng, Yuwei Du, Jie Zhao, Yong Li

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

Comments Accepted by NAACL 2025 as main conference paper, https://github.com/tsinghua-fib-lab/AgentMove

2404.07738 2025-02-11 cs.CL cs.AI cs.LG 67%

ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models

Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, Sung Ju Hwang

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

Comments NAACL 2025

2409.19808 2025-01-22 cs.CL cs.AI cs.LG 67%

Can Models Learn Skill Composition from Examples?

Haoyu Zhao, Simran Kaur, Dingli Yu, Anirudh Goyal, Sanjeev Arora

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

Comments Accepted to NeurIPS 2024

2412.17747 2024-12-24 cs.CL cs.AI cs.LG 67%

Deliberation in Latent Space via Differentiable Cache Augmentation

Luyang Liu, Jonas Pfeiffer, Jiaxing Wu, Jun Xie, Arthur Szlam

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

2406.14546 2024-12-24 cs.CL cs.AI cs.LG 67%

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

Johannes Treutlein, Dami Choi, Jan Betley, Samuel Marks, Cem Anil, Roger Grosse, Owain Evans

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

Comments Accepted at NeurIPS 2024. 10 pages, 8 figures

2412.12456 2024-12-18 cs.LG cs.AI cs.CL cs.DB 67%

Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks

Xunkai Li, Zhengyu Wu, Jiayi Wu, Hanwen Cui, Jishuo Jia, Rong-Hua Li, Guoren Wang

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

Comments In progress

2412.01132 2024-12-03 cs.CV 67%

Eyes on the Road: State-of-the-Art Video Question Answering Models Assessment for Traffic Monitoring Tasks

Joseph Raj Vishal, Divesh Basina, Aarya Choudhary, Bharatesh Chakravarthi

专题命中复杂问题求解：reasoning(abstract)；planning(abstract)

2411.16775 2024-11-27 cs.CL cs.AI cs.LG 67%

Parameter Efficient Instruction Tuning: An Empirical Study

Pengfei He

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

Comments 7 pages, 7 figures

2408.05646 2024-11-11 cs.LG cs.AI cs.CL 67%

Eigen Attention: Attention in Low-Rank Space for KV Cache Compression

Utkarsh Saxena, Gobinda Saha, Sakshi Choudhary, Kaushik Roy

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

Comments 12 page, 6 figures, 6 tables

2411.02223 2024-11-05 cs.CL cs.AI cs.LG 67%

Positive Experience Reflection for Agents in Interactive Text Environments

Philip Lippmann, Matthijs T. J. Spaan, Jie Yang

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

Comments To appear at NeurIPS 2024 Language Gamification workshop

2410.21784 2024-10-30 cs.AI cs.CL cs.LG cs.MA 67%

MARCO: Multi-Agent Real-time Chat Orchestration

Anubhav Shrimal, Stanley Kanagaraj, Kriti Biswas, Swarnalatha Raghuraman, Anish Nediyanchath, Yi Zhang, Promod Yenigalla

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

Comments EMNLP 2024 Industry Track

2410.09141 2024-10-15 cs.CL cs.AI cs.IR cs.LG 67%

ACER: Automatic Language Model Context Extension via Retrieval

Luyu Gao, Yunyi Zhang, Jamie Callan

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

2409.20053 2024-10-10 cs.AI cs.CL cs.LG 67%

GUNDAM: Aligning Large Language Models with Graph Understanding

Sheng Ouyang, Yulan Hu, Ge Chen, Yong Liu

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

1. 复杂问题求解 5001 篇

ToolRL: Reward is All Tool Learning Needs

F-LMM: Grounding Frozen Large Multimodal Models

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning

A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs

Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration

Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs

DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation

Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models

Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models

SPEX: Scaling Feature Interaction Explanations for LLMs

MoBA: Mixture of Block Attention for Long-Context LLMs

KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs

SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering

AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction

ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models

Can Models Learn Skill Composition from Examples?

Deliberation in Latent Space via Differentiable Cache Augmentation

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks

Eyes on the Road: State-of-the-Art Video Question Answering Models Assessment for Traffic Monitoring Tasks

Parameter Efficient Instruction Tuning: An Empirical Study

Eigen Attention: Attention in Low-Rank Space for KV Cache Compression

Positive Experience Reflection for Agents in Interactive Text Environments

MARCO: Multi-Agent Real-time Chat Orchestration

ACER: Automatic Language Model Context Extension via Retrieval

GUNDAM: Aligning Large Language Models with Graph Understanding