Retrieving a Set, Not Independent Passages: Set-Level Compatibility Learning for Efficient Set Exploration
About
Multi-hop question answering and retrieval-augmented reasoning require selecting evidence passages that are jointly useful for answering a query. However, most retrievers still score passages independently or make locally supervised sequential decisions, which can fail when evidence usefulness depends on compatibility among passages. LLM-based set selection can model such interactions, but its computational cost limits practical use. We address this gap by formulating multi-hop retrieval as query-set compatibility scoring and propose a set-level retrieval framework. Our training objective teaches retrievers to rank complete and compatible evidence sets above incomplete, noisy alternatives, making set scoring more robust to variable-length and partially noisy contexts. We instantiate the framework with two complementary set scorers: ParaSet, a lightweight late-interaction scorer that applies self-attention over precomputed bi-encoder embeddings for fast candidate-set exploration, and SetCE, a cross-encoder-based reranker trained with the same set-level objective. Experiments on various multi-hop QA benchmarks show that set-level compatibility learning improves retrieval performance and downstream QA task performance. We further show that the proposed set-level retrievers not only outperform document-level retrievers, but also exhibit complementary retrieval characteristics: combining their outputs yields stronger performance than simply retrieving more passages from a single document-level retriever.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Question Answering | 2Wiki | EM35.1 | 260 | |
| Question Answering | MuSiQue | EM9.3 | 57 | |
| Multi-hop Question Answering | MuSiQue | Exact Match (EM)11.88 | 25 | |
| Multi-hop Question Answering | HotpotQA (test val) | Exact Match (EM)42.9 | 18 | |
| Multi-hop Question Answering | 2WikiMultiHopQA (test val) | Exact Match (EM)35.3 | 16 | |
| Multi-hop Question Answering | MuSiQue (val test) | EM15.1 | 14 |