Lit3R：面向科学文献的基于证据的问答的检索-关联-阅读系统
Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature
浏览论文内容
中文总结 AI 辅助
Lit3R系统结合现成检索、重排序和LLM组件，通过迭代检索与跨论文证据综合，在LitTraceQA任务中排名第四，无需任务特定训练。
中文摘要 AI 辅助
我们描述了tus-nlp的Lit3R（检索-关联-阅读）系统，该系统用于LitTraceQA，一个基于文献的问答共享任务，要求系统检索相关论文、识别支持性证据并生成答案。Lit3R结合了现成的检索、重排序和大语言模型（LLM）组件，无需任务特定训练。检索器迭代地结合基于BM25的稀疏检索和密集检索、交叉编码器重排序以及基于LLM的验证，并通过论文到论文的扩展来补充基于问题的检索。阅读器首先在单篇论文中识别支持性证据，然后综合跨论文的证据以生成最终答案和证据轨迹。在官方测试集上，我们的系统在排行榜上排名第4。我们的代码可在以下网址获取：此https URL。
英文摘要
We describe tus-nlp's Lit3R (Retrieve-Relate-Read) system for LitTraceQA, a shared task for literature-grounded question answering that requires systems to retrieve relevant papers, identify supporting evidence, and generate answers. Lit3R combines off-the-shelf retrieval, reranking, and large language model (LLM) components without task-specific training. The retriever iteratively combines BM25-based sparse and dense retrieval, cross-encoder reranking, and LLM-based verification, and complements retrieval based on the question with paper-to-paper expansion. The reader first identifies supporting evidence within individual papers and then synthesizes evidence across papers to produce the final answer and evidence trace. On the official test set, our system ranked 4th on the leaderboard. Our code is available at https://github.com/tus-ist-nlp/littraceqa.
发表机构
- Tokyo University of Science（东京理科大学）
- Dentsu Soken Inc.（电通综研株式会社）
- Studio Ousia
机构由 AI 辅助整理，请以论文原文为准。
