Dual-view Training For Instruction-following Information Retrieval

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-param

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzeng2026dual

Related papers

• Towards Better Instruction Following Retrieval Models (2025)0.00
• Mfollowir: A Multilingual Benchmark For Instruction Following In Retrieval (2025)0.00
• Uniir: Training And Benchmarking Universal Multimodal Information Retrievers (2023)10.48
• Can Instructed Retrieval Models Really Support Exploration? (2026)0.00
• Evo-retriever: Llm-guided Curriculum Evolution With Viewpoint-pathway Collaboration For Multimodal Document Retrieval (2026)0.00
• IDMR: Towards Instance-driven Precise Visual Correspondence In Multimodal Retrieval (2025)2.29
• RETLLM: Training And Data-free Mllms For Multimodal Information Retrieval (2026)1.57
• Compositional Image Retrieval Via Instruction-aware Contrastive Learning (2024)0.00