Language model system improves document search without keyword matching
Retriever-Free Retrieval: Navigating Documents with Decision Models
Artificial Intelligence
Summary
Finding relevant information in large collections of documents usually depends on matching words or fixed patterns. This paper introduces DecisionRAG, a method that uses language models more like a person browsing a library, moving from broad topics to specific passages and deciding what to explore next without needing special training or initial keyword searches. The authors found that DecisionRAG can find better information faster than existing methods on several test sets. This approach helps language models better navigate and retrieve useful content from huge document collections.
What this means in practice
- •For enterprise search engineers: Build document search tools that find relevant passages without relying on keyword matching or initial retrievers.
- •For digital library developers: Create navigation-driven search interfaces that guide users through topics to find specific information in large text collections.
Authors
Chao Wan, Paul Jünger, Beixi Du, Bodong Liu, Navaneetha Krishnan, Kilian Q. Weinberger
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.