超越一次性扩展：面向多跳检索的对比证据探索
Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval
浏览论文内容
中文总结 AI 辅助
提出免训练多跳检索框架，通过证据条件探索、对比精炼和覆盖感知排序，提升多跳问答的检索质量与下游性能。
中文摘要 AI 辅助
检索增强生成（RAG）关键依赖于检索有效推理所需的证据。然而，在多跳问答（QA）中，这一任务仍具挑战性，因为支持性段落通常通过中间实体和关系相互关联，这些实体和关系必须逐步揭示。现有检索方法通常依赖单一检索意图或一次性查询扩展，限制了其适应新检索证据的能力，并可能引入噪声或冗余的检索信号。为解决这些局限，我们提出一种免训练的多跳检索框架，该框架整合了证据条件探索、段落特定对比精炼和覆盖感知的最终排序。在离线索引阶段，该框架构建段落特定的对比方面，这些方面相对于语义相似的邻居描述每个段落，提供细粒度信号以区分紧密相关的候选。在推理时，该框架迭代检索证据，生成针对未解决信息需求的探针，使用对比方面精炼候选相关性，并选择一组互补的段落，这些段落共同覆盖多样化的证据寻求意图。在MuSiQue、HotpotQA和2WikiMultihopQA上的实验表明，与基线相比，检索质量和下游QA性能均有一致提升。
英文摘要
Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective reasoning. However, this remains particularly challenging in multi-hop question answering (QA), where supporting passages are often linked through intermediate entities and relations that must be progressively uncovered. Existing retrieval approaches typically rely on a single retrieval intent or one-shot query expansion, limiting their ability to adapt to newly retrieved evidence and potentially introducing noisy or redundant retrieval signals. To address these limitations, we propose a training-free multi-hop retrieval framework that integrates evidence-conditioned exploration, passage-specific contrastive refinement, and coverage-aware final ranking. During offline indexing, the framework constructs passage-specific contrastive facets that characterize each passage relative to its semantically similar neighbors, providing fine-grained signals to distinguish closely related candidates. At inference time, the framework iteratively retrieves evidence, generates probes targeting unresolved information needs, refines candidate relevance using the contrastive facets, and selects a complementary set of passages that collectively cover diverse evidence-seeking intents. Experiments on MuSiQue, HotpotQA, and 2WikiMultihopQA demonstrate consistent improvements in retrieval quality and downstream QA performance over baselines.
发表机构
- Chung-Ang University（中央大学）
机构由 AI 辅助整理，请以论文原文为准。
