思想交换：通过跨模型通信增强大语言模型能力
Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication
AI总结：
本文提出思想交换（EoT）框架，通过记忆、报告、中继和辩论四种跨模型通信范式并引入置信度评估机制，以低成本显著提升大语言模型在复杂推理任务上的表现。
摘要：
大语言模型（LLMs）近期通过思维链（Chain-of-Thought）技术在复杂推理任务上取得了显著进展。尽管如此，其推理往往受限于自身内在理解，缺乏外部见解。为解决这一问题，我们提出了思想交换（Exchange-of-Thought，EoT），这是一个在问题求解过程中实现跨模型通信的新颖框架。受网络拓扑结构启发，EoT 整合了四种独特的通信范式：记忆（Memory）、报告（Report）、中继（Relay）和辩论（Debate）。本文深入探讨了每种范式所涉及的通信动态与通信量。为抵消错误推理链带来的风险，我们在这些通信中实现了一种稳健的置信度评估机制。我们在多种复杂推理任务上的实验表明，EoT 显著超越了已有基线方法，凸显了外部见解在提升 LLM 性能方面的价值。此外，我们还表明 EoT 能够以具有成本效益的方式取得这些优越结果，标志着高效协作式人工智能问题求解领域的一项有前景的进展。
英文摘要：
Large Language Models (LLMs) have recently made significant strides in complex reasoning tasks through the Chain-of-Thought technique. Despite this progress, their reasoning is often constrained by their intrinsic understanding, lacking external insights. To address this, we propose Exchange-of-Thought (EoT), a novel framework that enables cross-model communication during problem-solving. Drawing inspiration from network topology, EoT integrates four unique communication paradigms: Memory, Report, Relay, and Debate. This paper delves into the communication dynamics and volume associated with each paradigm. To counterbalance the risks of incorrect reasoning chains, we implement a robust confidence evaluation mechanism within these communications. Our experiments across diverse complex reasoning tasks demonstrate that EoT significantly surpasses established baselines, underscoring the value of external insights in enhancing LLM performance. Furthermore, we show that EoT achieves these superior results in a cost-effective manner, marking a promising advancement for efficient and collaborative AI problem-solving.
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。
