让用户可视化并修改大模型的推理过程，提升可控性与可信度。
Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
- 将模型推理过程转为可交互的层级主题图
- 用户可快速修正错误、添加思路、优化输出
- 适合需要精准控制生成逻辑的决策场景
大语言模型（LLMs）通过生成链式思维（CoT）内容来提升输出质量，但这些推理过程冗长且无结构，难以审查。同时缺乏用户反馈机制，无法删减不当推论或补充关键假设。本文提出交互式推理（Interactive Reasoning），将链式思维以层级主题形式可视化，并支持用户审阅与修改。我们在原型系统Hippo中实现该功能，用于面对不确定权衡的AI辅助决策。16名参与者参与的用户研究显示，交互式推理使用户能快速识别并中断错误生成，高效引导模型生成定制化回应，并更清晰理解模型推理与输出。本工作推动了将用户监督融入大模型推理的新范式。
原文摘要 · Abstract (English)
The output quality of large language models (LLMs) can be improved via "reasoning": generating segments of chain-of-thought (CoT) content to further condition the model prior to producing user-facing output. While these chains contain valuable information, they are verbose and lack explicit organization, making them tedious to review. Moreover, they lack opportunities for user feedback, such as to remove unwanted considerations, add desired ones, or clarify unclear assumptions. We introduce Interactive Reasoning, an interaction design that visualizes chain-of-thought outputs as a hierarchy of topics and enables user review and modification. We implement interactive reasoning in Hippo, a prototype for AI-assisted decision making in the face of uncertain trade-offs. In a user study with 16 participants, we find that interactive reasoning in Hippo allows users to quickly identify and interrupt erroneous generations, efficiently steer the model towards customized responses, and better understand both model reasoning and model outputs. Our work contributes to a new paradigm that incorporates user oversight into LLM reasoning processes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。