做文献综述或学术研究的团队终于有了一个靠谱的问答工具——直接提取原文片段，彻底告别幻觉。用 ACL 论文的 NLP 研究者可以直接试试这个开源方案。
ACL-Verbatim 是一个基于提取式问答的系统，专门用于从 ACL Anthology 研究论文中直接提取原文片段，避免大语言模型常见的幻觉问题。研究者构建了一个新的基准数据集，包含合成用户查询与论文片段配对，并由 NLP 专家进行人工标注。一个 1.5 亿参数的 ModernBERT 分词分类器在该基准上取得了最佳词级 F1 分数（53.6），超过了最强的大语言模型提取器（48.7）。该系统为学术研究者提供了一种可靠、高效的信息检索方式，尤其适合需要精确引用的场景。
ACL-Verbatim: hallucination-free question answering for research
Academic researchers need efficient and reliable methods for collecting high-quality information from trusted sources, but modern tools for AI-assisted research still suffer from the tendency of Large Language Models (LLMs) to produce factually inaccurate or nonsensical output, commonly referred to as hallucinations. We apply the extractive question answering system VerbatimRAG to research papers in the ACL Anthology, directly mapping user queries to verbatim text spans in retrieved documents. We contribute a novel ground truth dataset for the task of mapping user queries to relevant text spans in research papers, and use it to train and evaluate a variety of extractive models. Human annotation is performed by NLP researchers and is based on synthetic user queries generated using a custom pipeline based on the ScIRGen methodology, paired with chunks of research papers retrieved by VerbatimRAG. On this benchmark, a 150M-parameter ModernBERT token classifier trained on silver supervision from our pipeline achieves the best word-level F1 (53.6), ahead of the strongest evaluated LLM extractor (48.7).