Efficient Tool Use with Chain-of-Abstraction Reasoning
EPFL(洛桑联邦理工学院)
Silin Gao, Jane Dwivedi-Yu, Ping Yu, Xiaoqing Ellen Tan, Ramakanth Pasunuru, Olga Golovneva, Koustuv Sinha, Asli Celikyilmaz, Antoine Bosselut, Tianlu Wang
To achieve faithful reasoning that aligns with human expectations, large language models (LLMs) need to ground their reasoning to real-world knowledge (e.g., web facts, math and physical rules). Tools help LLMs access this external knowledge, but there remains challenges for fine-tuning LLM agents (e.g., Toolformer) to invoke tools in multi-step reasoning problems, where inter-connected tool calls require holistic and efficient tool usage planning.
In this work, we propose a new method for LLMs to better leverage tools in multi-step reasoning. Our method, Chain-of-Abstraction (CoA), trains LLMs to first decode reasoning chains with abstract placeholders, and then call domain tools to reify each reasoning chain by filling in specific knowledge. This planning with abstract chains enables LLMs to learn more general reasoning strategies, which are robust to shifts of domain knowledge (e.g., math results) relevant to different reasoning questions. It also allows LLMs to perform decoding and calling of external tools in parallel, which avoids the inference delay caused by waiting for tool responses. In mathematical reasoning and Wiki QA domains, we show that our method consistently outperforms previous chain-of-thought and tool-augmented baselines on both in-distribution and out-of-distribution test sets, with an average ~6% absolute QA accuracy improvement. LLM agents trained with our method also show more efficient tool use, with inference speed being on average ~1.4x faster than baseline tool-augmented LLMs.
Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
Idiap Research Institute(Idiap 研究所);School of Informatics, University of Edinburgh(爱丁堡大学信息学院);School of Computer Science, University of Sheffield(谢菲尔德大学计算机科学学院);Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系);National Biomarker Centre (NBC), CRUK Manchester Institute(英国癌症研究中心曼彻斯特研究所国家生物标志物中心)
Abstraction-of-Thought Makes Language Models Better Reasoners
Institute for Artificial Intelligence, Tsinghua University(清华大学人工智能学院);Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心);Tencent AI Lab(腾讯AI实验室)
Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models
Centro de Investigación en Ciencias, Universidad Autónoma del Estado de Morelos(莫雷洛斯州自治大学科学研究中心)
How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality
State Key Laboratory of AI Safety(人工智能安全国家重点实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Beijing University of Post and Telecommunications(北京邮电大学)
AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
Department of Mathematical Sciences National Chengchi University Taipei Taiwan(数学科学系 国立政治大学 台北 台湾);Department of Computer Science National Chengchi University Taipei Taiwan(计算机科学系 国立政治大学 台北 台湾);Institute of Information Science Academia Sinica Taipei Taiwan(信息科学研究所 中国学术院 台北 台湾);National Chengchi University(国立政治大学)
Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models
Human Centric ART, University of Rome Tor Vergata(人类中心ART,罗马大学托尔维加塔分校);ILCC, School of Informatics, University of Edinburgh(ILCC,信息学院,爱丁堡大学);School of Computer Science, University of Sheffield(计算机科学学院,谢菲尔德大学);Almawave S.p.A.(Almawave公司)
Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering
College of Zhiyuan, Shanghai Jiao Tong University(上海交通大学致远学院);School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院);Shanghai Jiao Tong University(上海交通大学)
Question Answering as Global Reasoning over Semantic Abstractions
University of Illinois, Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Pennsylvania(宾夕法尼亚大学);Allen Institute for Artificial Intelligence (AI2)(艾伦人工智能研究所(AI2))
ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering
Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore(新加坡高性能计算研究所,科技研究局);Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore(科技研究局前沿人工智能研究中心,新加坡);College of Computing and Data Science, Nanyang Technological University, Singapore(新加坡南洋理工大学计算与数据科学学院)