RAGAPHENE：一个带有人工增强与编辑功能的RAG标注平台
RAGAPHENE: A RAG Annotation Platform with Human Enhancements and Edits
AI总结：
本文提出RAGAPHENE聊天标注平台，通过人工增强与编辑支持标注者模拟真实多轮RAG对话，已由约40名标注者构建数千条对话，用于评估LLM的事实正确性并减少幻觉。
摘要：
当事实正确性至关重要时，检索增强生成（RAG）是与大语言模型（LLM）对话的一个重要方面。LLM可能给出看似正确但包含幻觉信息的答案。因此，构建能够在多轮RAG对话上评估LLM的基准已成为一项日益重要的任务。模拟真实世界对话对于生成高质量评估基准至关重要。我们提出了RAGAPHENE，一个基于聊天的标注平台，使标注者能够模拟真实世界对话，用于对LLM进行基准测试和评估。RAGAPHENE已被约40名标注者成功使用，构建了数千个真实世界对话。
英文摘要：
Retrieval Augmented Generation (RAG) is an important aspect of conversing with Large Language Models (LLMs) when factually correct information is important. LLMs may provide answers that appear correct, but could contain hallucinated information. Thus, building benchmarks that can evaluate LLMs on multi-turn RAG conversations has become an increasingly important task. Simulating real-world conversations is vital for producing high quality evaluation benchmarks. We present RAGAPHENE, a chat-based annotation platform that enables annotators to simulate real-world conversations for benchmarking and evaluating LLMs. RAGAPHENE has been successfully used by approximately 40 annotators to build thousands of real-world conversations.
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。
