语言大模型 / LLM - arXivDaily 专题

2408.00754 2024-11-22 cs.CV cs.LG 83%

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model

Benlin Liu, Yuhao Dong, Yiqin Wang, Zixian Ma, Yansong Tang, Luming Tang, Yongming Rao, Wei-Chiu Ma, Ranjay Krishna

专题命中推理与问题求解：language model(title,abstract)；prompting(abstract)；分类 cs.LG

Comments project page: https://coarse-correspondence.github.io

2411.12591 2024-11-20 cs.CV cs.AI 83%

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

Haojie Zheng, Tianyang Xu, Hanchi Sun, Shu Pu, Ruoxi Chen, Lichao Sun

专题命中推理与问题求解：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.AI

2411.05755 2024-11-11 cs.RO cs.CL cs.CV 83%

End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering

Dylan Goetting, Himanshu Gaurav Singh, Antonio Loquercio

专题命中推理与问题求解：language model(title,abstract)；prompting(abstract)；分类 cs.CL

2406.11709 2024-11-08 cs.CL cs.MA 83%

Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging

Priyanka Kargupta, Ishika Agarwal, Dilek Hakkani-Tur, Jiawei Han

专题命中推理与问题求解：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Code available at: https://github.com/agarwalishika/TreeInstruct Accepted at EMNLP'24 Findings

2409.11527 2024-11-06 cs.AI 83%

Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent

Fatemeh Haji, Mazal Bethany, Maryam Tabar, Jason Chiang, Anthony Rios, Peyman Najafirad

专题命中推理与问题求解：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.AI

2408.02248 2024-11-06 cs.CL cs.MA cs.SE 83%

ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems

Andrew Zhu, Liam Dugan, Chris Callison-Burch

专题命中推理与问题求解：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments EMNLP 2024 (Demo Track)

2411.00828 2024-11-05 cs.CV cs.LG 83%

Dreaming Out Loud: A Self-Synthesis Approach For Training Vision-Language Models With Developmentally Plausible Data

Badr AlKhamissi, Yingtian Tang, Abdülkadir Gökce, Johannes Mehrer, Martin Schrimpf

专题命中推理与问题求解：language model(title,abstract)；large language model(abstract)；分类 cs.LG

Comments Accepted to BabyLM Challenge at CoNLL 2024

2411.00640 2024-11-04 stat.AP cs.CL 83%

Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations

Evan Miller

专题命中推理与问题求解：language model(title,abstract)；large language model(abstract)；分类 cs.CL

Comments 14 pages

2410.16198 2024-10-22 cs.AI cs.CV 83%

Improve Vision Language Model Chain-of-thought Reasoning

Ruohong Zhang, Bowen Zhang, Yanghao Li, Haotian Zhang, Zhiqing Sun, Zhe Gan, Yinfei Yang, Ruoming Pang, Yiming Yang

专题命中推理与问题求解：language model(title,abstract)；preference optimization(abstract)；分类 cs.AI

Comments 10 pages + appendix

2402.19350 2024-10-17 cs.CL 83%

Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process

Guangming Huang, Yunfei Long, Cunjin Luo, Jiaxing Shen, Xia Sun

专题命中推理与问题求解：prompting(title,abstract)；language model(abstract)；分类 cs.CL

Comments This paper has been accepted at COLING 2024

2405.01379 2024-10-14 cs.CL 83%

Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving

Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas

专题命中推理与问题求解：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Camera-ready for EMNLP 2024

2410.06237 2024-10-10 cs.RO cs.AI 83%

BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation

Rutav Shah, Albert Yu, Yifeng Zhu, Yuke Zhu, Roberto Martín-Martín

专题命中推理与问题求解：language model(title,abstract)；foundation model(abstract)；分类 cs.AI

Comments 7 Figures, 2 Tables, 11 Pages

2405.14252 2024-10-10 cs.LG 83%

Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting

Qingxiang Liu, Xu Liu, Chenghao Liu, Qingsong Wen, Yuxuan Liang

专题命中推理与问题求解：foundation model(title,abstract)；language model(abstract)；分类 cs.LG

2406.16078 2024-10-08 cs.CL 83%

First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning

Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi, Shusaku Sone, Masaya Taniguchi, Keisuke Sakaguchi, Kentaro Inui

专题命中推理与问题求解：language model(title,abstract)；prompting(abstract)；分类 cs.CL

Comments This paper is accepted at EMNLP 2024

2410.03907 2024-10-08 cs.CL 83%

ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual Language Models in Household Activities

Ying Su, Zhan Ling, Haochen Shi, Jiayang Cheng, Yauwai Yim, Yangqiu Song

专题命中推理与问题求解：language model(title,abstract)；large language model(abstract)；分类 cs.CL

Comments 13 pages, 9 figures, 8 tables, accepted to EMNLP 2024 main conference

2406.00257 2024-10-07 cs.CL 83%

Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs

Mohammed Saidul Islam, Raian Rahman, Ahmed Masry, Md Tahmid Rahman Laskar, Mir Tafseer Nayeem, Enamul Hoque

专题命中推理与问题求解：language model(title,abstract)；large language model(abstract)；分类 cs.CL

2406.14732 2024-10-02 cs.CL cs.IR 83%

TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarization

Jayetri Bardhan, Bushi Xiao, Daisy Zhe Wang

专题命中推理与问题求解：prompting(title,abstract)；language model(abstract)；分类 cs.CL

2409.20385 2024-10-01 cs.CL 83%

Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation

Shan Chen, Mingye Gao, Kuleen Sasse, Thomas Hartvigsen, Brian Anthony, Lizhou Fan, Hugo Aerts, Jack Gallifant, Danielle Bitterman

专题命中推理与问题求解：language model(title,abstract)；large language model(abstract)；分类 cs.CL

Comments Submitted for Review

2401.10065 2024-10-01 cs.CL 83%

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs

Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych

专题命中推理与问题求解：prompting(title,abstract)；LLM(abstract)；分类 cs.CL

Comments EMNLP Main 2024. Code, prompt templates, prompts, and outputs are publicly available at https://github.com/UKPLab/arxiv2024-conditional-reasoning-llms

2406.04197 2024-09-24 cs.CL 83%

DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning

Shangqing Tu, Kejian Zhu, Yushi Bai, Zijun Yao, Lei Hou, Juanzi Li

专题命中推理与问题求解：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 13 pages, 7 figures

2403.16437 2024-09-24 cs.SE cs.CL 83%

Reasoning Runtime Behavior of a Program with LLM: How Far Are We?

Junkai Chen, Zhiyuan Pan, Xing Hu, Zhenhao Li, Ge Li, Xin Xia

专题命中推理与问题求解：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted by 47th IEEE/ACM International Conference on Software Engineering (ICSE 2025). Our REval leaderboard is available at https://r-eval.github.io

2409.09788 2024-09-17 cs.CV cs.CL 83%

Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models

Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler, David Acuna

专题命中推理与问题求解：language model(title,abstract)；prompting(abstract)；分类 cs.CL

Comments 20 pages, 13 figures

2307.00329 2024-09-17 cs.RO cs.AI 83%

DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment

Yanjiang Guo, Yen-Jen Wang, Lihan Zha, Jianyu Chen

专题命中推理与问题求解：language model(title,abstract)；large language model(abstract)；分类 cs.AI

Comments Published in IROS 2024

2407.14133 2024-09-13 cs.CL 83%

I Know About "Up"! Enhancing Spatial Reasoning in Visual Language Models Through 3D Reconstruction

Zaiqiao Meng, Hao Zhou, Yifang Chen

专题命中推理与问题求解：language model(title,abstract)；prompting(abstract)；分类 cs.CL

2408.14504 2024-08-28 cs.SE cs.AI cs.PL 83%

Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes

Heejae Chon, Seonghyeon Lee, Jinyoung Yeo, Dongha Lee

专题命中推理与问题求解：language model(title,abstract)；prompting(abstract)；分类 cs.AI

Comments 15pages, 6 figures, 8 tables

2407.03600 2024-08-28 cs.CL 83%

Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models

Jay Shim, Grant Kruttschnitt, Alyssa Ma, Daniel Kim, Benjamin Chek, Athul Anand, Kevin Zhu, Sean O'Brien

专题命中推理与问题求解：language model(title,abstract)；prompting(abstract)；分类 cs.CL

2310.06830 2024-08-27 cs.CL 83%

Lemur: Harmonizing Natural Language and Code for Language Agents

Yiheng Xu, Hongjin Su, Chen Xing, Boyu Mi, Qian Liu, Weijia Shi, Binyuan Hui, Fan Zhou, Yitao Liu, Tianbao Xie, Zhoujun Cheng, Siheng Zhao, Lingpeng Kong, Bailin Wang, Caiming Xiong, Tao Yu

专题命中推理与问题求解：language agent(title,abstract)；language model(abstract)；分类 cs.CL

Comments ICLR 2024 Spotlight; https://github.com/OpenLemur/Lemur

2401.08565 2024-08-26 cs.CL 83%

Tuning Language Models by Proxy

Alisa Liu, Xiaochuang Han, Yizhong Wang, Yulia Tsvetkov, Yejin Choi, Noah A. Smith

专题命中推理与问题求解：language model(title,abstract)；pretraining(abstract)；分类 cs.CL

Comments COLM 2024 camera-ready, code available at https://github.com/alisawuffles/proxy-tuning

2408.01682 2024-08-06 cs.CL cs.CV 83%

Multi-Frame Vision-Language Model for Long-form Reasoning in Driver Behavior Analysis

Hiroshi Takato, Hiroshi Tsutsui, Komei Soda, Hidetaka Kamigaito

专题命中推理与问题求解：language model(title,abstract)；instruction tuning(abstract)；分类 cs.CL

Comments On-going work

2407.21293 2024-08-01 cs.CV cs.AI 83%

SimpleLLM4AD: An End-to-End Vision-Language Model with Graph Visual Question Answering for Autonomous Driving

Peiru Zheng, Yun Zhao, Zhan Gong, Hong Zhu, Shaohua Wu

专题命中推理与问题求解：language model(title,abstract)；large language model(abstract)；分类 cs.AI

Comments 16 pages, 3 figures

1. 推理与问题求解 18971 篇

Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination

End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering

Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging

Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent

ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems

Dreaming Out Loud: A Self-Synthesis Approach For Training Vision-Language Models With Developmentally Plausible Data

Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations

Improve Vision Language Model Chain-of-thought Reasoning

Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process

Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving

BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation

Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting

First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning

ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual Language Models in Household Activities

Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs

TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarization

Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs

DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning

Reasoning Runtime Behavior of a Program with LLM: How Far Are We?

Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models

DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment

I Know About "Up"! Enhancing Spatial Reasoning in Visual Language Models Through 3D Reconstruction

Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes

Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models

Lemur: Harmonizing Natural Language and Code for Language Agents

Tuning Language Models by Proxy

Multi-Frame Vision-Language Model for Long-form Reasoning in Driver Behavior Analysis

SimpleLLM4AD: An End-to-End Vision-Language Model with Graph Visual Question Answering for Autonomous Driving