arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.17464cs.CL
收藏

使用抽象链推理实现高效工具使用

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

AI总结:

提出 Chain-of-Abstraction 方法,让 LLM 先规划抽象推理链再并行调用工具填实知识,在数学推理与 Wiki QA 上提升准确率约6%、推理速度约1.4倍。

摘要:

为了实现符合人类预期的可信推理,大型语言模型(LLM)需要将其推理建立在现实世界知识(例如网络事实、数学和物理规则)的基础上。工具帮助 LLM 获取这些外部知识,但在多步推理问题中微调 LLM 智能体(例如 Toolformer)以调用工具仍存在挑战,因为相互关联的工具调用需要整体且高效的工具使用规划。在本工作中,我们提出了一种让 LLM 在多步推理中更好地利用工具的新方法。我们的方法 Chain-of-Abstraction(CoA,抽象链)训练 LLM 首先解码带有抽象占位符的推理链,然后调用领域工具,通过填入具体知识来具象化每条推理链。这种基于抽象链的规划使 LLM 能够学习更通用的推理策略,这些策略对与不同推理问题相关的领域知识(例如数学结果)变化具有鲁棒性。它还允许 LLM 并行执行外部工具的解码与调用,从而避免因等待工具响应而导致的推理延迟。在数学推理和 Wiki QA 领域,我们表明,在分布内和分布外测试集上,我们的方法均持续优于先前的思维链和工具增强基线,QA 准确率平均绝对提升约 6%。使用我们的方法训练的 LLM 智能体还表现出更高效的工具使用,推理速度平均比工具增强基线 LLM 快约 1.4 倍。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑