ReVoicer：以人为中心、由大语言模型辅助的同行评审对话式语音标注系统
ReVoicer: Conversational Voice Annotation for Human-Centered, LLM-Assisted Peer Review
浏览论文内容
中文总结 AI 辅助
该研究提出ReVoicer原型系统，支持评审人员阅读论文时对话式语音标注，借助大语言模型润色、分类并锚定评论，最终基于评审人员自身评论生成符合风格指南的评审意见，计划与ISMAR社区开展评估。
中文摘要 AI 辅助
我们提出ReVoicer，这是一款支持同行评审人员阅读论文时与论文对话的原型系统。评审人员高亮某段文本后，可说出（或输入）思路式评论；大语言模型会结合周围文本上下文对该评论进行润色，按评论类型标记，并将其锚定到对应段落。评审人员完成阅读后，ReVoicer会对照特定会议的评审标准检查累计笔记，报告覆盖缺口，且仅基于评审人员自身的评论，按照从其过往评审中提炼的风格指南撰写评审意见。该系统不会生成自身的批评意见。我们阐述了系统的设计原理与实现，并概述了未来评估计划；将与ISMAR社区一道收集反馈，探讨系统设计、额外功能构想及评估方案。
英文摘要
We present ReVoicer, a prototype system that supports peer reviewers by letting them converse with a paper as they read it. The reviewer highlights a passage and speaks (or types) a train-of-thought comment. A large language model then cleans the comment using the surrounding prose as context, tags it by comment type, and anchors it to the passage. After the reviewer finishes reading, ReVoicer checks the accumulated notes against a venue-specific rubric and reports coverage gaps to assist with further reflection. Then ReVoicer drafts a review composed from the reviewer's comments, written to a style guide distilled from the reviewer's past reviews. We describe the system's design rationale and implementation, and we outline plans for future evaluations.
