R$^3$ Prompting：面向噪声上下文下大型语言模型思维链推理的Review、Rephrase与Resolve
R$^3$ Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context
AI总结：
针对大型语言模型在噪声上下文中推理不准确的问题，提出R$^3$ prompting交互式提示方法，通过关键句提取、变量声明和答案预测三步提升推理准确率，实验证明其鲁棒性与泛化能力。
摘要：
在思维链（CoT）提示的帮助下，大型语言模型（LLMs）在各种推理任务上取得了显著的性能。然而，大多数模型都在无噪声上下文中进行评估，LLMs在噪声上下文下产生不准确结果的困境尚未得到充分研究。现有研究利用触发语句来鼓励LLMs集中于相关信息，但触发器对最终答案预测的影响有限。受交互式CoT方法启发，即通过用户与LLMs之间的多轮交互来促进中间推理步骤，我们提出了一种新颖的提示方法，即R$^3$ prompting，用于噪声上下文下的CoT推理。具体而言，R$^3$ prompting与LLMs交互以执行关键句提取、变量声明和答案预测，这对应于Review、Rephrase和Resolve的思考过程。上一次交互生成的响应将作为提示，指导下一次交互的响应。我们的实验表明，在噪声上下文下的五个推理任务中，R$^3$ prompting显著优于现有的CoT提示方法。使用GPT-3.5-turbo，我们观察到在噪声上下文下的推理任务上，与最具竞争力的提示基线相比，平均准确率提高了3.7%。更多的分析和消融研究表明了R$^3$ prompting方法在解决LLMs在噪声上下文下推理任务时的鲁棒性和泛化能力。
英文摘要：
With the help of Chain-of-Thought (CoT) prompting, Large Language Models (LLMs) have achieved remarkable performance on various reasoning tasks. However, most of them have been evaluated under noise-free context and the dilemma for LLMs to produce inaccurate results under the noisy context has not been fully investigated. Existing studies utilize trigger sentences to encourage LLMs to concentrate on the relevant information but the trigger has limited effect on final answer prediction. Inspired by interactive CoT method, where intermediate reasoning steps are promoted by multiple rounds of interaction between users and LLMs, we propose a novel prompting method, namely R$^3$ prompting, for CoT reasoning under noisy context. Specifically, R$^3$ prompting interacts with LLMs to perform key sentence extraction, variable declaration and answer prediction, which corresponds to a thought process of reviewing, rephrasing and resolving. The responses generated at the last interaction will perform as hints to guide toward the responses of the next interaction. Our experiments show that R$^3$ prompting significantly outperforms existing CoT prompting methods on five reasoning tasks under noisy context. With GPT-3.5-turbo, we observe 3.7% accuracy improvement on average on the reasoning tasks under noisy context compared to the most competitive prompting baseline. More analyses and ablation studies show the robustness and generalization of R$^3$ prompting method in solving reasoning tasks in LLMs under noisy context.
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。
