大模型推理能力 - arXivDaily 专题

2403.04306 2024-10-29 cs.CV cs.AI cs.LG 62%

Effectiveness Assessment of Recent Large Vision-Language Models

Yao Jiang, Xinyu Yan, Ge-Peng Ji, Keren Fu, Meijun Sun, Huan Xiong, Deng-Ping Fan, Fahad Shahbaz Khan

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

Comments Accepted by Visual Intelligence

Journal ref Visual Intelligence, 2024, Vol. 2, article no. 17

2410.18146 2024-10-25 cs.CL cs.AI cs.PL 62%

Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation

Chandra Irugalbandara

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

2410.16670 2024-10-23 cs.LG cs.AI 62%

CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing

Chen Yang, Chenyang Zhao, Quanquan Gu, Dongruo Zhou

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

Comments 25 pages, 5 tables, 3 figures

2410.14897 2024-10-22 cs.CL cs.AI 62%

From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items

Melissa Roemmele, Andrew S. Gordon

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

Comments Accepted at Findings of EMNLP 2024

2410.14072 2024-10-21 cs.CV cs.AI cs.CL 62%

Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers

Yuxin Wen, Qingqing Cao, Qichen Fu, Sachin Mehta, Mahyar Najibi

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

2404.17524 2024-10-21 cs.AI cs.CL 62%

On the Use of Large Language Models to Generate Capability Ontologies

Luis Miguel Vieira da Silva, Aljosha Köcher, Felix Gehlhoff, Alexander Fay

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

Comments \c{opyright} 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

2410.13298 2024-10-18 cs.CL cs.AI 62%

Advancing Large Language Model Attribution through Self-Improving

Lei Huang, Xiaocheng Feng, Weitao Ma, Liang Zhao, Yuchun Fan, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

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

Comments Accepted by EMNLP 2024 Main Conference

2410.12859 2024-10-18 cs.CL cs.AI cs.IR 62%

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism

Yimin Tang, Yurong Xu, Ning Yan, Masood Mortazavi

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

2406.14928 2024-10-18 cs.AI cs.CL cs.HC cs.MA cs.SI 62%

Autonomous Agents for Collaborative Task under Information Asymmetry

Wei Liu, Chenxi Wang, Yifei Wang, Zihao Xie, Rennai Qiu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Chen Qian

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

Comments 32 pages, 12 figures, 6 tables, accepted by NeurIPS 2024, see detail at https://thinkwee.top/iagents

2410.12959 2024-10-18 cs.AI cs.CL 62%

Large Language Models as a Tool for Mining Object Knowledge

Hannah YoungEun An, Lenhart K. Schubert

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

2312.03003 2024-10-17 cs.HC cs.AI cs.CL 62%

Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation

Sunjae Lee, Junyoung Choi, Jungjae Lee, Munim Hasan Wasi, Hojun Choi, Steven Y. Ko, Sangeun Oh, Insik Shin

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

2410.11437 2024-10-16 cs.CL cs.AI 62%

Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs

Sihang Zhao, Youliang Yuan, Xiaoying Tang, Pinjia He

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

Comments EMNLP 2024 Findings

2401.10712 2024-10-15 cs.CV cs.AI cs.CL 62%

Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge

Haibo Wang, Weifeng Ge

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

Comments Accepted by ECCV'24

2406.19934 2024-10-14 cs.CL cs.AI 62%

From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis

Chuanqi Cheng, Jian Guan, Wei Wu, Rui Yan

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

Comments Accepted by EMNLP 2024

2410.08292 2024-10-14 cs.LG cs.AI stat.ML 62%

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?

Khashayar Gatmiry, Nikunj Saunshi, Sashank J. Reddi, Stefanie Jegelka, Sanjiv Kumar

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

2408.00727 2024-10-14 cs.CL cs.AI 62%

Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions

Guangzhi Xiong, Qiao Jin, Xiao Wang, Minjia Zhang, Zhiyong Lu, Aidong Zhang

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

Comments Accepted to PSB 2025

2410.06667 2024-10-11 cs.CL cs.AI 62%

Large Language Models as Code Executors: An Exploratory Study

Chenyang Lyu, Lecheng Yan, Rui Xing, Wenxi Li, Younes Samih, Tianbo Ji, Longyue Wang

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

2402.15048 2024-10-11 cs.CL cs.AI 62%

Unlocking the Power of Large Language Models for Entity Alignment

Xuhui Jiang, Yinghan Shen, Zhichao Shi, Chengjin Xu, Wei Li, Zixuan Li, Jian Guo, Huawei Shen, Yuanzhuo Wang

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

2410.05210 2024-10-08 cs.CV cs.AI cs.CL 62%

Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality

Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, In So Kweon, Junmo Kim

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

Comments EMNLP 2024 (Long, Main). Project page: https://ytaek-oh.github.io/fsc-clip

2406.12034 2024-10-08 cs.CL cs.LG 62%

Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts

Junmo Kang, Leonid Karlinsky, Hongyin Luo, Zhen Wang, Jacob Hansen, James Glass, David Cox, Rameswar Panda, Rogerio Feris, Alan Ritter

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

2406.11234 2024-10-02 cs.CL cs.AI 62%

MiniConGTS: A Near Ultimate Minimalist Contrastive Grid Tagging Scheme for Aspect Sentiment Triplet Extraction

Qiao Sun, Liujia Yang, Minghao Ma, Nanyang Ye, Qinying Gu

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

Comments arXiv admin note: text overlap with arXiv:2403.07342

2409.14924 2024-09-24 cs.CL cs.AI 62%

Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely

Siyun Zhao, Yuqing Yang, Zilong Wang, Zhiyuan He, Luna K. Qiu, Lili Qiu

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

2409.12425 2024-09-20 cs.CL cs.LG 62%

Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels

Chaoqun Liu, Qin Chao, Wenxuan Zhang, Xiaobao Wu, Boyang Li, Anh Tuan Luu, Lidong Bing

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

Comments 15 pages

2409.09916 2024-09-17 cs.CL cs.AI 62%

SFR-RAG: Towards Contextually Faithful LLMs

Xuan-Phi Nguyen, Shrey Pandit, Senthil Purushwalkam, Austin Xu, Hailin Chen, Yifei Ming, Zixuan Ke, Silvio Savarese, Caiming Xong, Shafiq Joty

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

Comments Technical report

2409.07747 2024-09-13 cs.CV cs.AI cs.CL 62%

Multi-object event graph representation learning for Video Question Answering

Yanan Wang, Shuichiro Haruta, Donghuo Zeng, Julio Vizcarra, Mori Kurokawa

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

Comments presented at MIRU2024

2409.00255 2024-09-04 cs.CV cs.AI cs.CL cs.GR cs.HC 62%

MAPWise: Evaluating Vision-Language Models for Advanced Map Queries

Srija Mukhopadhyay, Abhishek Rajgaria, Prerana Khatiwada, Vivek Gupta, Dan Roth

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

Comments 30 Pages, 46 Tables, 6 Figure

2409.00135 2024-09-04 cs.CL cs.AI 62%

HoneyComb: A Flexible LLM-Based Agent System for Materials Science

Huan Zhang, Yu Song, Ziyu Hou, Santiago Miret, Bang Liu

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

Comments Under Review on EMNLP 2024

2212.10537 2024-09-02 cs.CV cs.AI cs.CL 62%

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

Martha Lewis, Nihal V. Nayak, Peilin Yu, Qinan Yu, Jack Merullo, Stephen H. Bach, Ellie Pavlick

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

Comments Lewis and Nayak contributed equally

Journal ref In Findings of the Association for Computational Linguistics, EACL 2024, pages 1487 - 1500, Malta. Association for Computational Linguistics

2406.18312 2024-08-29 cs.CL cs.AI 62%

AI-native Memory: A Pathway from LLMs Towards AGI

Jingbo Shang, Zai Zheng, Jiale Wei, Xiang Ying, Felix Tao, Mindverse Team

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

2405.05109 2024-08-27 cs.CL cs.AI 62%

QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs

Weijia Zhang, Vaishali Pal, Jia-Hong Huang, Evangelos Kanoulas, Maarten de Rijke

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

Comments Accepted by the 27th European Conference on Artificial Intelligence (ECAI-2024)

1. 复杂问题求解 5001 篇

Effectiveness Assessment of Recent Large Vision-Language Models

Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation

CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing

From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items

Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers

On the Use of Large Language Models to Generate Capability Ontologies

Advancing Large Language Model Attribution through Self-Improving

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism

Autonomous Agents for Collaborative Task under Information Asymmetry

Large Language Models as a Tool for Mining Object Knowledge

Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation

Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs

Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge

From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?

Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions

Large Language Models as Code Executors: An Exploratory Study

Unlocking the Power of Large Language Models for Entity Alignment

Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality

Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts

MiniConGTS: A Near Ultimate Minimalist Contrastive Grid Tagging Scheme for Aspect Sentiment Triplet Extraction

Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely

Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels

SFR-RAG: Towards Contextually Faithful LLMs

Multi-object event graph representation learning for Video Question Answering

MAPWise: Evaluating Vision-Language Models for Advanced Map Queries

HoneyComb: A Flexible LLM-Based Agent System for Materials Science

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models

AI-native Memory: A Pathway from LLMs Towards AGI

QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs