无需标注数据，用大模型自动生成训练信号，提升多跳问答的检索效果。
ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision
- 利用大模型判断文档与问题相关性及答案一致性，生成监督信号。
- 在三个基准上实现超越现有方法的检索与问答性能。
- 适合研究多跳问答、无监督训练或想减少标注依赖的开发者。
多跳问答（MHQA）需跨多个文档推理以回答复杂问题。稠密检索器虽优于稀疏方法（如BM25），但需标注的查询-文档对进行微调。由于推理过程中问题形式多样，标注成本高。为此，我们提出ReSCORE：一种无需标注文档的稠密检索器训练方法。ReSCORE利用大语言模型评估文档与问题的相关性及其与正确答案的一致性，并在迭代问答框架中训练检索器。在三个MHQA基准上的实验表明，ReSCORE显著提升了检索效果，实现了当前最优的多跳问答性能。代码已开源：https://leeds1219.github.io/ReSCORE。
原文摘要 · Abstract (English)
Multi-hop question answering (MHQA) involves reasoning across multiple documents to answer complex questions. Dense retrievers typically outperform sparse methods like BM25 by leveraging semantic embeddings; however, they require labeled query-document pairs for fine-tuning. This poses a significant challenge in MHQA due to the high variability of queries (reformulated) questions throughout the reasoning steps. To overcome this limitation, we introduce Retriever Supervision with Consistency and Relevance (ReSCORE), a novel method for training dense retrievers for MHQA without labeled documents. ReSCORE leverages large language models to capture each documents relevance to the question and consistency with the correct answer and use them to train a retriever within an iterative question-answering framework. Experiments on three MHQA benchmarks demonstrate the effectiveness of ReSCORE, with significant improvements in retrieval, and in turn, the state-of-the-art MHQA performance. Our implementation is available at: https://leeds1219.github.io/ReSCORE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。