arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.07099cs.CLcs.AIcs.GTcs.LG
收藏

Nash CoT:基于偏好均衡的多路径推理

Nash CoT: Multi-Path Inference with Preference Equilibrium

School of Engineering, Westlake University(西湖大学工程学院);University of Cambridge(剑桥大学)

Ziqi Zhang, Cunxiang Wang, Xiong Xiao, Yue Zhang, Donglin Wang

AI总结:

本文提出Nash CoT方法,通过在多路径推理中构建博弈系统平衡角色特定与通用LLM的生成,在减少推理路径数量的同时保持推理多样性和准确率。

摘要:

思维链(CoT)是一种能够提升大语言模型(LLMs)在复杂推理任务上表现的推理框架。在各类与CoT相关的研究中,多路径推理作为一种简单而有效的改进方法尤为突出。然而,推理路径的数量并不存在最优设定。因此,为了获得更好的结果,我们不得不增加推理路径的数量,这反过来又增加了推理成本。为了解决这一局限性,我们可以利用与问题相关的角色模板将LLMs引导到相关角色中,从而提高每条路径进行正确推理的可能性,进一步降低对推理路径数量的依赖,同时提升推理准确率。然而,将LLMs置于特定角色中可能会降低其推理多样性,并在少数角色依赖度较低的任务上降低性能。为了缓解LLM过度沉浸于特定角色的情况,我们提出了Nash CoT,通过在每条路径上构建一个博弈系统来平衡角色特定LLM的生成与通用LLM的生成,从而既保证有效的角色采纳,又保持LLM生成的多样性,进一步在减少推理路径数量需求的同时维持多路径推理的性能。我们在多种推理任务上评估了Nash CoT,包括阿拉伯语推理、常识问答和符号推理,在推理路径数量相同的情况下取得了与多路径CoT相当或更好的结果。

英文摘要:

Chain of thought (CoT) is a reasoning framework that can enhance the performance of Large Language Models (LLMs) on complex inference tasks. In particular, among various studies related to CoT, multi-path inference stands out as a simple yet effective improvement. However, there is no optimal setting for the number of inference paths. Therefore, we have to increase the number of inference paths to obtain better results, which in turn increases the inference cost. To address this limitation, we can utilize question-related role templates to guide LLMs into relevant roles, thereby increasing the possibility of correct inferences for each path and further reducing dependence on the number of inference paths while improving reasoning accuracy. However, placing LLMs into specific roles may reduce their reasoning diversity and performance on a few tasks where role dependence is low. To alleviate the excessive immersion of the LLM into a specific role, we propose Nash CoT by constructing a game system on each path that balances the generation from role-specific LLMs' and the general LLMs' generation, thereby ensuring both effective role adoption and diversity in LLM generation further maintaining the performance of multi-path inference while reducing the requirement of the number of inference paths. We evaluate Nash CoT across various inference tasks, including Arabic Reasoning, Commonsense Question Answering, and Symbolic Inference, achieving results that are comparable to or better than those of multi-path CoT with the equal number of inference paths.

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。

↑