Can Instructed Retrieval Models Really Support Exploration?

Abstract

Exploratory searches are characterized by under-specified goals and evolving query intents. In such scenarios, retrieval models that can capture user-specified nuances in query intent and adapt results accordingly are desirable -- instruction-following retrieval models promise such a capability. In this work, we evaluate instructed retrievers for the prevalent yet under-explored application of aspect-conditional seed-guided exploration using an expert-annotated test collection. We evaluate both recent LLMs fine-tuned for instructed retrieval and general-purpose LLMs prompted for ranking with the highly performant Pairwise Ranking Prompting. We find that the best instructed retrievers improve on ranking relevance compared to instruction-agnostic approaches. However, we also find that instruction following performance, crucial to the user experience of interacting with models, does not mirror ranking relevance improvements and displays insensitivity or counter-intuitive behavior to instr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymaheshwari2026can

Related papers

• Expandr: Teaching Dense Retrievers Beyond Queries With LLM Guidance (2025)3.25
• Dual-view Training For Instruction-following Information Retrieval (2026)0.00
• Rar-b: Reasoning As Retrieval Benchmark (2024)2.68
• Mfollowir: A Multilingual Benchmark For Instruction Following In Retrieval (2025)0.00
• Optimizing Retrieval For RAG Via Reinforcement Learning (2025)0.00
• Rare: Retrieval Augmented Retrieval With In-context Examples (2024)0.00
• Few-shot Prompting For Pairwise Ranking: An Effective Non-parametric Retrieval Model (2024)5.84
• Interpreting Search Result Rankings Through Intent Modeling (2018)0.00