Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication
This addresses the problem of constrained reasoning in LLMs for AI researchers and practitioners, offering an incremental improvement through collaborative communication.
The paper tackles the limitation of LLMs in complex reasoning by proposing Exchange-of-Thought (EoT), a framework for cross-model communication, which significantly outperforms baselines in diverse tasks and does so cost-effectively.
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.