Large Language Models (LLMs) frequently suffer from knowledge-intensive questions, often being inconsistent by providing different outputs despite given the same input. The response quality worsens when the user expresses a firm opposing stance which causes the LLMs to adjust its response despite the correct initial one. These behaviors decrease the reliability and validity of the responses provided by these models. In this paper, we attempt to 1) raise awareness of the inherent risks that follow from overly relying on AI agents like ChatGPT by showing how Chain-of-Feedback (CoF) triggers LLMs to deviate more from the actual answer and 2) suggest a novel prompting method, Recursive Chain of Feedback (R-CoF), that we are conducting further study. The CoF system takes in an open-ended multi-step question. Then, we repetitively provide meaningless feedback requesting another attempt. Our preliminary experiments show that such feedback only decreases the quality of the response. On the other hand, to mitigate the effects of the aforementioned inconsistencies, we present a novel method of recursively revising the initial incorrect reasoning provided by the LLM by repetitively breaking down each incorrect step into smaller individual problems.

翻译：大型语言模型（LLMs）在处理知识密集型问题时频繁表现出不一致性，即便面对相同输入也会生成不同输出。当用户表达坚定的对立立场时，LLMs会调整其初始正确响应，导致响应质量进一步恶化。这些行为降低了模型输出响应的可靠性与有效性。本文旨在：1）通过展示链式反馈（CoF）如何诱导LLMs偏离真实答案，揭示过度依赖ChatGPT等AI代理的固有风险；2）提出一种新型提示方法——递归链式反馈（R-CoF），该方法目前正在深入研究。CoF系统接收开放式多步骤问题，随后通过重复提供无意义反馈要求模型重新生成答案。初步实验表明，此类反馈只会降低响应质量。为缓解上述不一致性效应，我们提出一种通过将LLM初始错误推理的每个错误步骤递归分解为更小独立问题来进行迭代修正的新方法。