语言大模型 / LLM - arXivDaily 专题

2310.12342 2023-11-16 cs.CL cs.AI 79%

Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking

Yongqi Tong, Yifan Wang, Dawei Li, Sizhe Wang, Zi Lin, Simeng Han, Jingbo Shang

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

2310.01420 2023-11-15 cs.CL cs.AI cs.HC 79%

Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems

Robin Schmucker, Meng Xia, Amos Azaria, Tom Mitchell

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

Comments NeurIPS'23 GAIED, Camera-ready

2305.11243 2023-11-09 cs.CL cs.AI 79%

Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responses

Eliza Kosoy, Emily Rose Reagan, Leslie Lai, Alison Gopnik, Danielle Krettek Cobb

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

Comments 9 pages, 7 figures

2304.11015 2023-11-06 cs.CL cs.AI cs.DB cs.HC 79%

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction

Mohammadreza Pourreza, Davood Rafiei

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

Comments To appear in NeurIPS 2023

2310.17140 2023-10-27 cs.CL cs.AI 79%

Symbolic Planning and Code Generation for Grounded Dialogue

Justin T. Chiu, Wenting Zhao, Derek Chen, Saujas Vaduguru, Alexander M. Rush, Daniel Fried

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

Comments Accepted to EMNLP 2023

2306.15724 2023-10-18 cs.RO cs.AI cs.CL cs.CV 79%

REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction

Zeyi Liu, Arpit Bahety, Shuran Song

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

Comments Conference on Robot Learning (CoRL) 2023; Project website: https://robot-reflect.github.io/

2310.01089 2023-10-03 cs.CL cs.LG 79%

GraphText: Graph Reasoning in Text Space

Jianan Zhao, Le Zhuo, Yikang Shen, Meng Qu, Kai Liu, Michael Bronstein, Zhaocheng Zhu, Jian Tang

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

Comments Preprint. Work in progress

2309.09843 2023-09-19 cs.CL cs.LG cs.SD eess.AS 79%

Instruction-Following Speech Recognition

Cheng-I Jeff Lai, Zhiyun Lu, Liangliang Cao, Ruoming Pang

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

2305.14020 2023-09-14 cs.CL cs.AI 79%

Does ChatGPT have Theory of Mind?

Bart Holterman, Kees van Deemter

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

2309.04663 2023-09-13 cs.CL cs.AI 79%

FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning

Xinyi Wang, John Wieting, Jonathan H. Clark

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

2308.16763 2023-09-08 cs.CL cs.AI 79%

Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection

Kairui Hu, Ming Yan, Joey Tianyi Zhou, Ivor W. Tsang, Wen Haw Chong, Yong Keong Yap

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

Comments 5 pages, 2 figures, 2 tables

2309.00667 2023-09-06 cs.CL cs.LG 79%

Taken out of context: On measuring situational awareness in LLMs

Lukas Berglund, Asa Cooper Stickland, Mikita Balesni, Max Kaufmann, Meg Tong, Tomasz Korbak, Daniel Kokotajlo, Owain Evans

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

2302.08468 2023-09-04 cs.LG cs.CL cs.PL cs.SE 79%

LEVER: Learning to Verify Language-to-Code Generation with Execution

Ansong Ni, Srini Iyer, Dragomir Radev, Ves Stoyanov, Wen-tau Yih, Sida I. Wang, Xi Victoria Lin

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

Comments ICML'23; code available at https://github.com/niansong1996/lever

2308.10380 2023-08-24 cs.AI cs.CL 79%

A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability

Ming Jin, Bilgehan Sel, Fnu Hardeep, Wotao Yin

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

2308.10444 2023-08-22 cs.CL cs.AI cs.HC 79%

Dynamic Strategy Chain: Dynamic Zero-Shot CoT for Long Mental Health Support Generation

Qi Chen, Dexi Liu

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

2308.09658 2023-08-22 cs.CL cs.AI cs.CV 79%

Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning

Pengbo Hu, Ji Qi, Xingyu Li, Hong Li, Xinqi Wang, Bing Quan, Ruiyu Wang, Yi Zhou

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

Comments 16 pages,1 figures, under review

2308.07921 2023-08-16 cs.CL cs.AI cs.CV 79%

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

Aojun Zhou, Ke Wang, Zimu Lu, Weikang Shi, Sichun Luo, Zipeng Qin, Shaoqing Lu, Anya Jia, Linqi Song, Mingjie Zhan, Hongsheng Li

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

Comments Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

2308.04445 2023-08-10 cs.LG cs.AI 79%

Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyc

Doug Lenat, Gary Marcus

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

Comments 21 pages, 1 Figure

2308.01157 2023-08-08 stat.ML cs.AI cs.LG 79%

LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs

Benjamin J. Lengerich, Sebastian Bordt, Harsha Nori, Mark E. Nunnally, Yin Aphinyanaphongs, Manolis Kellis, Rich Caruana

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

2305.02897 2023-08-04 cs.CL cs.AI 79%

An automatically discovered chain-of-thought prompt generalizes to novel models and datasets

Konstantin Hebenstreit, Robert Praas, Louis P Kiesewetter, Matthias Samwald

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

2305.00909 2023-07-20 cs.PL cs.AI cs.LG 79%

Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation

Wenqing Zheng, S P Sharan, Ajay Kumar Jaiswal, Kevin Wang, Yihan Xi, Dejia Xu, Zhangyang Wang

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

Comments Accepted in ICML 2023

2307.07930 2023-07-18 cs.CL cs.AI 79%

GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT

Yifan Zhang, Cheng Wei, Shangyou Wu, Zhengting He, Wenhao Yu

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

Comments 23 pages, 4 figures

2307.01644 2023-07-06 cs.HC cs.AI cs.CL 79%

Insert-expansions for Tool-enabled Conversational Agents

Andreas Göldi, Roman Rietsche

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

2306.14325 2023-06-29 cs.AI cs.LG 79%

The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs

Lance Ying, Katherine M. Collins, Megan Wei, Cedegao E. Zhang, Tan Zhi-Xuan, Adrian Weller, Joshua B. Tenenbaum, Lionel Wong

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

Comments To appear at ICML Workshop on Theory of Mind in Communicating Agents

2306.07932 2023-06-26 cs.CL cs.AI 79%

Human-in-the-Loop through Chain-of-Thought

Zefan Cai, Baobao Chang, Wenjuan Han

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

2306.08647 2023-06-21 cs.RO cs.AI cs.LG 79%

Language to Rewards for Robotic Skill Synthesis

Wenhao Yu, Nimrod Gileadi, Chuyuan Fu, Sean Kirmani, Kuang-Huei Lee, Montse Gonzalez Arenas, Hao-Tien Lewis Chiang, Tom Erez, Leonard Hasenclever, Jan Humplik, Brian Ichter, Ted Xiao, Peng Xu, Andy Zeng, Tingnan Zhang, Nicolas Heess, Dorsa Sadigh, Jie Tan, Yuval Tassa, Fei Xia

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

Comments https://language-to-reward.github.io/

2301.10521 2023-06-06 cs.CL cs.AI cs.IR 79%

ExaRanker: Explanation-Augmented Neural Ranker

Fernando Ferraretto, Thiago Laitz, Roberto Lotufo, Rodrigo Nogueira

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

2304.11116 2023-05-12 cs.AI cs.LG 79%

Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT

Jiawei Zhang

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

Comments 34 pages, 3 figures, 8 tables

2301.12050 2023-04-28 cs.LG cs.CL 79%

Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling

Kolby Nottingham, Prithviraj Ammanabrolu, Alane Suhr, Yejin Choi, Hannaneh Hajishirzi, Sameer Singh, Roy Fox

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

Comments in proceedings of ICML 23

2304.06588 2023-04-14 cs.CL cs.AI cs.SI 79%

ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning

Petter Törnberg

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

Comments 5 pages, 3 figures

1. 推理与问题求解 19037 篇

Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking

Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems

Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responses

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction

Symbolic Planning and Code Generation for Grounded Dialogue

REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction

GraphText: Graph Reasoning in Text Space

Instruction-Following Speech Recognition

Does ChatGPT have Theory of Mind?

FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning

Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection

Taken out of context: On measuring situational awareness in LLMs

LEVER: Learning to Verify Language-to-Code Generation with Execution

A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability

Dynamic Strategy Chain: Dynamic Zero-Shot CoT for Long Mental Health Support Generation

Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyc

LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs

An automatically discovered chain-of-thought prompt generalizes to novel models and datasets

Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation

GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT

Insert-expansions for Tool-enabled Conversational Agents

The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs

Human-in-the-Loop through Chain-of-Thought

Language to Rewards for Robotic Skill Synthesis

ExaRanker: Explanation-Augmented Neural Ranker

Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT

Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling

ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning