Dual-View Training for Instruction-Following Information Retrieval

• URL: http://arxiv.org/abs/2604.18845v1
• Date: Mon, 20 Apr 2026 21:10:29 GMT
• Title: Dual-View Training for Instruction-Following Information Retrieval
• Abstract summary: We propose a dual-view data synthesis strategy based on polarity reversal.<n>We show that our method improves performance on the FollowIR benchmark by 45%.
• Score: 9.741583305127994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruction-following information retrieval (IF-IR) studies retrieval systems that must not only find documents relevant to a query, but also obey explicit user constraints such as required attributes, exclusions, or output preferences. However, most retrievers are trained primarily for semantic relevance and often fail to distinguish documents that match the topic from those that satisfy the instruction. We propose a dual-view data synthesis strategy based on polarity reversal: given a query, a document that is relevant under the instruction, and a hard negative that matches the query but violates the instruction, we prompt an LLM to generate a complementary instruction under which the two documents swap relevance labels. By presenting the same document pair under complementary instructions that invert their relevance labels, the training signal forces the retriever to reconsider the same candidate set through the instruction, rather than relying on fixed topical cues. On a 305M-parameter encoder, our method improves performance on the FollowIR benchmark by 45%, surpassing general-purpose embedding models of comparable or larger scale. Through head-to-head comparisons at matched data budgets, we further show that data diversity and instruction supervision play complementary roles: the former preserves general retrieval quality, while the latter improves instruction sensitivity. These results highlight the value of targeted data synthesis for building retrieval systems that are both broadly capable and instruction-aware.

Related papers

• Training Documents Reranker with Search Rubrics for Deep Research Agent [54.08506174105984]
  We propose search-oriented rubrics that textitexplicitly define the requirements that high-quality document sets should satisfy.<n>We further train a document reranker textbfRubricRanker to select a high-quality subset from retrieved documents.
  arXiv  Detail & Related papers  (2026-08-04T12:11:14Z)
• Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors [2.5681874692250193]
  We investigate whether supervised bi-encoder retrievers implicitly learn a document-level relevance prior.<n>We find that supervised neural retrievers encode relevance priors that generalize to unseen documents and are consistent across models.<n>We find that judged-relevant documents tend to be comprehensive, self-contained summaries of mainstream topics, while niche, fragmentary, or highly technical content is often left unjudged.
  arXiv  Detail & Related papers  (2026-06-01T19:31:28Z)
• Align then Train: Efficient Retrieval Adapter Learning [16.855103318831073]
  We propose a label-efficient framework that trains retrieval adapters in two stages: self-supervised alignment and supervised adaptation.<n>Experiments on the MAIR benchmark, spanning 126 retrieval tasks across 6 domains, show that ERA improves retrieval in low-label settings.
  arXiv  Detail & Related papers  (2026-04-03T19:04:42Z)
• Can Instructed Retrieval Models Really Support Exploration? [29.8124798158787]
  Best instructed retrievers improve on ranking relevance compared to instruction-agnostic approaches.<n>While users may benefit from using current instructed retrievers over instruction-agnostic models, they may not benefit from using them for long-running exploratory sessions.
  arXiv  Detail & Related papers  (2026-01-16T01:45:29Z)
• Improving Document Retrieval Coherence for Semantically Equivalent Queries [63.97649988164166]
  We propose a variation of the Multi-Negative Ranking loss for training DR that improves the coherence of models in retrieving the same documents.<n>The loss penalizes discrepancies between the top-k ranked documents retrieved for diverse but semantic equivalent queries.
  arXiv  Detail & Related papers  (2025-08-11T13:34:59Z)
• Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance [30.879299174443812]
  In this work, we forgo real documents and annotations and use large language models to generate synthetic documents.<n>Our experiments on MS MARCO and BEIR benchmark show that our proposed approach outperforms conventional training with InfoNCE by a large margin.
  arXiv  Detail & Related papers  (2025-03-29T22:33:22Z)
• DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval [10.770281363775148]
  We propose a novel and general generative retrieval framework, namely Leveraging Document-Oriented Contrastive Learning in Generative Retrieval (DOGR)<n>It adopts a two-stage learning strategy that captures the relationship between queries and documents comprehensively through direct interactions.<n>Negative sampling methods and corresponding contrastive learning objectives are implemented to enhance the learning of semantic representations.
  arXiv  Detail & Related papers  (2025-02-11T03:25:42Z)
• Generative Retrieval Meets Multi-Graded Relevance [104.75244721442756]
  We introduce a framework called GRaded Generative Retrieval (GR$2$) GR$2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. Experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR$2$.
  arXiv  Detail & Related papers  (2024-09-27T02:55:53Z)
• PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval [76.50690734636477]
  We propose PromptReps, which combines the advantages of both categories: no need for training and the ability to retrieve from the whole corpus. The retrieval system harnesses both dense text embedding and sparse bag-of-words representations.
  arXiv  Detail & Related papers  (2024-04-29T04:51:30Z)
• ExcluIR: Exclusionary Neural Information Retrieval [74.08276741093317]
  We present ExcluIR, a set of resources for exclusionary retrieval. evaluation benchmark includes 3,452 high-quality exclusionary queries. training set contains 70,293 exclusionary queries, each paired with a positive document and a negative document.
  arXiv  Detail & Related papers  (2024-04-26T09:43:40Z)
• Questions Are All You Need to Train a Dense Passage Retriever [123.13872383489172]
  ART is a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. It uses a new document-retrieval autoencoding scheme, where (1) an input question is used to retrieve a set of evidence documents, and (2) the documents are then used to compute the probability of reconstructing the original question.
  arXiv  Detail & Related papers  (2022-06-21T18:16:31Z)

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.