Cross-Disciplinary Research · arXiv:2610.35868
Retriever-Free Retrieval: Navigating Documents with Decision Models
Authors: Chao Wan, Paul Jünger, Beixi Du, Bodong Liu, Navaneetha Krishnan et al. (arXiv:2610.35868) · arXiv: 2610.35868
Core Methodological Innovation
Featured in Nujan's Cross-Disciplinary Research Literature Digest. Open side-by-side with interactive equation, methodology, and citation breakdowns.
Key Quantitative & Theoretical Takeaway: Open arXiv:2610.35868 in Nujan to inspect every mathematical symbol, experimental baseline, and citation directly alongside the original PDF.
Abstract
While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.
Step-by-Step Equation & Methodology Breakdown
What is Retriever-Free Retrieval: Navigating Documents with Decision Models (arXiv:2610.35868) about?
While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.
How can I read arXiv:2610.35868 with interactive explanations?
Visit https://nujan.app/abs/2610.35868 to open Retriever-Free Retrieval: Navigating Documents with Decision Models in Nujan's split-screen research workspace with instant equation and methodology breakdowns.