检索一个集合，而非独立段落：用于高效集合探索的集合级兼容性学习

中文摘要 AI 辅助

多跳问答和检索增强推理需要选择对回答查询有用的证据段落。大多数检索器仍独立对段落评分或进行局部监督的顺序决策，当证据有用性取决于段落间兼容性时可能失败。基于大语言模型的集合选择可建模这种交互，但计算成本限制实际应用。我们将多跳检索表述为查询-集合兼容性评分来解决这一差距，提出集合级检索框架。训练目标使检索器将完整且兼容的证据集排在不完整、有噪声的替代集之上，让集合评分对可变长度和部分有噪声的上下文更稳健。我们用两个互补的集合评分器实例化框架：ParaSet，一个轻量级的后期交互评分器，通过对预计算的双编码器嵌入应用自注意力进行快速候选集探索；SetCE，一个基于交叉编码器的重排器，用相同的集合级目标训练。在各种多跳问答基准上的实验表明，集合级兼容性学习提高了检索性能和下游问答任务性能。我们还表明，所提出的集合级检索器不仅优于文档级检索器，还展现出互补的检索特性：组合它们的输出比从单个文档级检索器简单检索更多段落性能更强。

英文摘要

Multi-hop question answering requires retrieving multiple evidence passages whose usefulness often depends on one another. Conventional retrievers either rank passages independently or construct evidence sequentially through locally supervised next-passage decisions. Sequential conditioning captures some cross-passage dependencies, but its local extension scores do not provide a common criterion for comparing complete evidence sets of different compositions and sizes. Existing multi-hop retrievers therefore avoid directly learning a query--set compatibility function over complete evidence sets, as the exponentially large set space is daunting to cover during learning and impractical to search at inference time. To overcome these challenges, we formulate multi-hop retrieval by directly ranking candidate evidence sets with an energy-based query--set compatibility score $s_θ(q,S)$, learned from informative contrasts without exhaustive coverage or normalization of the combinatorial set space. Given a gold evidence set, we automatically generate contrasts by adding, removing, or replacing passages, yielding rich set-level supervision without additional annotation. To make search over this combinatorial space practical at inference time, we introduce a novel retrieve-and-rerank framework over the set space: ParaSet, a lightweight scorer over precomputed passage representations for efficient set exploration, and SetCE, an expressive cross-encoder for set reranking. Our experiments show that set-level retrieval consistently provides a complementary signal to passage-level relevance, becoming relatively more effective when more hops are required to reach evidence from the query. Motivated by this complementarity, combining the two signals further improves downstream QA performance, outperforming both deeper passage-level retrieval and an ensemble of distinct passage-level retrievers.

发表机构

• Seoul National University（首尔大学）
• Graduate School of Data Science（数据科学研究生院）

机构由 AI 辅助整理，请以论文原文为准。