Imrnns: An Efficient Method For Interpretable Dense Retrieval Via Embedding Modulation

Abstract

Interpretability in black-box dense retrievers remains a central challenge in Retrieval-Augmented Generation (RAG). Understanding how queries and documents semantically interact is critical for diagnosing retrieval behavior and improving model design. However, existing dense retrievers rely on static embeddings for both queries and documents, which obscures this bidirectional relationship. Post-hoc approaches such as re-rankers are computationally expensive, add inference latency, and still fail to reveal the underlying semantic alignment. To address these limitations, we propose Interpretable Modular Retrieval Neural Networks (IMRNNs), a lightweight framework that augments any dense retriever with dynamic, bidirectional modulation at inference time. IMRNNs employ two independent adapters: one conditions document embeddings on the current query, while the other refines the query embedding using corpus-level feedback from initially retrieved documents. This iterative modulation process

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysaxena2026imrnns

Related papers

• Expandr: Teaching Dense Retrievers Beyond Queries With LLM Guidance (2025)3.25
• Llm-augmented Retrieval: Enhancing Retrieval Models Through Language Models And Doc-level Embedding (2024)0.00
• Nemotron Colembed V2: Top-performing Late Interaction Embedding Models For Visual Document Retrieval (2026)0.00
• Rethinking Hybrid Retrieval: When Small Embeddings And LLM Re-ranking Beat Bigger Models (2025)0.00
• Rzenembed: Towards Comprehensive Multimodal Retrieval (2025)0.00
• Mor: Better Handling Diverse Queries With A Mixture Of Sparse, Dense, And Human Retrievers (2025)2.26
• Reasoning-augmented Representations For Multimodal Retrieval (2026)0.00
• Revela: Dense Retriever Learning Via Language Modeling (2025)0.00