Retrieving a Set, Not Independent Passages: Set-Level Compatibility Learning for Efficient Set Exploration

• URL: http://arxiv.org/abs/2607.05712v1
• Date: Tue, 07 Jul 2026 00:37:45 GMT
• Title: Retrieving a Set, Not Independent Passages: Set-Level Compatibility Learning for Efficient Set Exploration
• Abstract summary: We formulate multi-hop retrieval as query-set compatibility scoring and propose a set-level retrieval framework.<n>Our training objective teaches retrievers to rank complete and compatible evidence sets above incomplete, noisy alternatives.<n>We instantiate the framework with two complementary set scorers: ParaSet, a lightweight late-interaction scorer, and SetCE, a cross-encoder-based reranker.
• Score: 14.89719169791929
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 papers

• Retriever Portfolios: A Principled Approach to Adaptive RAG [30.668406304237404]
  We propose a method that automatically selects a small, diverse subset of retrievers from a large pool of candidates, to cover different regions of the target query distribution.<n>Across multiple QA benchmarks, our learned portfolios and router pipeline consistently outperform single-retriever and naive multi-retriever baselines.
  arXiv  Detail & Related papers  (2026-05-29T11:43:05Z)
• Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA [11.316299961548415]
  We propose a paradigm that performs implicit query rewriting directly at the embedding level.<n>By context-subtractive query steering, GRAIL excels at compositional cross-modal reasoning.<n>By dynamically routing queries based on task type, our Hybrid Framework achieves a 40.3% macro-averaged performance gain on MultimodalQA.
  arXiv  Detail & Related papers  (2026-05-27T15:46:21Z)
• R$^3$AG: Retriever Routing for Retrieval-Augmented Generation [59.47703698994575]
  R$3$AG decomposes retriever capability into two learnable dimensions: retrieval quality and generation utility.<n>R$3$AG consistently outperforms both the best individual retrievers and state-of-the-art static routing methods.
  arXiv  Detail & Related papers  (2026-04-22T06:51:20Z)
• CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search [51.911048955965136]
  CoSearch is a framework that jointly trains a multi-step reasoning agent and a generative document ranking model.<n>Our results show that joint training of the reasoning agent and retrieval system is both feasible and strongly performant.
  arXiv  Detail & Related papers  (2026-04-19T17:48:17Z)
• Agentic-R: Learning to Retrieve for Agentic Search [82.43426728778418]
  We propose a novel retriever training framework tailored for agentic search.<n>Unlike retrievers designed for single-turn retrieval-augmented generation (RAG), we propose to use both local query-passage relevance and global answer correctness.<n>Our retriever, termed ours, consistently outperforms strong baselines across different search agents.
  arXiv  Detail & Related papers  (2026-01-17T02:59:54Z)
• Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning [6.212994999785976]
  TOOLQP is a lightweight framework that models retrieval as iterative query planning.<n>It decomposes instructions into sub-tasks and dynamically generates queries to interact with the retriever.<n>It achieves state-of-the-art performance, exhibiting superior zero-shot generalization, robustness across diverse retrievers, and significant improvements in downstream agentic execution.
  arXiv  Detail & Related papers  (2026-01-12T17:58:39Z)
• DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval [36.38599923075882]
  DIVER is a retrieval pipeline designed for reasoning-intensive information retrieval.<n>It consists of four components: the document preprocessing stage, the query expansion stage, the retrieval stage and the reranking stage.<n>On the BRIGHT benchmark, DIVER achieves state-of-the-art nDCG@10 scores of 45.8 overall and 28.9 on original queries, consistently outperforming competitive reasoning-aware models.
  arXiv  Detail & Related papers  (2025-08-11T13:57:49Z)
• LTRR: Learning To Rank Retrievers for LLMs [53.285436927963865]
  We show that routing-based RAG systems can outperform the best single-retriever-based systems.<n>Performance gains are especially pronounced in models trained with the Answer Correctness (AC) metric.<n>As part of the SIGIR 2025 LiveRAG challenge, our submitted system demonstrated the practical viability of our approach.
  arXiv  Detail & Related papers  (2025-06-16T17:53:18Z)
• Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts [67.67746334493302]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks.<n>We propose a tri-encoder sequential retriever that models this process as a Markov Decision Process (MDP)<n>We show that our method consistently and significantly outperforms baselines, underscoring the importance of explicitly modeling inter-example dependencies.
  arXiv  Detail & Related papers  (2025-04-15T17:35:56Z)
• Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer [80.50327229467993]
  We show that a single model trained end-to-end can achieve both competitive retrieval and QA performance. We show that end-to-end adaptation significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings.
  arXiv  Detail & Related papers  (2022-12-05T04:51:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.