Mutable Transcripts：可编辑对话历史减少上下文污染
Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
有人把聊天记录做成了可编辑的：改一句话，历史里过时的内容直接消失，17 人实测大家都更喜欢，代码还开源了。
一篇 arXiv 论文提出 mutable transcripts 交互范式，用户可通过自然语言编辑请求修改此前的对话轮次，而不是只能追加消息，从而消除过时信息造成的上下文污染。
研究团队开发了集成对话历史修订功能的原型 ReChat，并开展 n=17 的受控用户研究。结果显示参与者在清晰度、信心和易用性上显著偏好可编辑记录，且重启对话的意愿更低。
对话分析表明该方法能缩短对话长度并清除过时的保留上下文。
Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
Contemporary large language model (LLM) chat systems treat conversation history as an immutable sequence of turns that defines the model's working context. However, user intent in real interactions is not static: it evolves through correction, refinement, and shifting constraints. This mismatch between dynamic intent and static transcripts can result in context pollution, where outdated or irrelevant information persists and continues to influence subsequent responses. We introduce mutable transcripts, a new interaction paradigm that enables users to revise prior turns through natural language edit requests, allowing the conversation history itself to be updated rather than appended. This reframes the transcript from a passive record into an editable representation of conversational state. We present a working prototype that integrates transcript-level revision into a standard chat interface and evaluate its feasibility through a controlled user study (n=17) and an illustrative transcript analysis of representative interaction scenarios. Participants significantly preferred mutable transcripts over standard chat across measures of clarity, confidence, and ease of use, with reduced intent to restart conversations. Transcript analysis of representative user study conversations shows that mutable transcripts can reduce conversation length and eliminate obsolete retained context. These findings provide initial evidence that user-driven revision of conversational history can improve interaction quality and help maintain a more current representation of user intent. The source code and prototype can be accessed at https://github.com/QxLabIreland/ReChat
本条情报归属 AITOP「论文」核心栏目，重点聚焦欧洲人工智能治理与技术生态。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：上下文污染、对话系统、LLM、用户研究，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Dan Barry, Andrew Hines），经 AITOP 多维评分管线结构化提炼。
