Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies

• URL: http://arxiv.org/abs/2605.29384v1
• Date: Thu, 28 May 2026 05:36:37 GMT
• Title: Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies
• Abstract summary: We propose Latent Terms, a method revealing that models trained for dense retrieval learn representations that can trivially be decomposed into sparse features.<n>When trained on frozen retrievers, Sparse Autoencoders without any retrieval-specific adjustments extract a latent vocabulary with approximately Zipfian collection statistics.<n>Latent Terms is able to match or outperform single-vector scoring methods from its own base model as well as comparable SPLADE variants.
• Score: 1.938658977168075
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose Latent Terms, a method revealing that models trained for dense retrieval, whether single- or multi-vector, learn representations that can trivially be decomposed into retrieval-ready sparse features. When trained on frozen retrievers, Sparse Autoencoders without any retrieval-specific adjustments extract a latent vocabulary with approximately Zipfian collection statistics, directly suitable for classical sparse retrieval scoring via BM25. This approach enables sparse retrieval while requiring no learned expansion objective or sparse retrieval supervision whatsoever, and can be readily applied to any dense retriever. Latent Terms is able to match or outperform single-vector scoring methods from its own base model as well as comparable SPLADE variants. In addition, it substantially outperforms its base model on LIMIT, a task specifically designed to highlight the failures of single-vector retrieval. Overall, our results highlight that neural retrievers contain more expressive and indexable structure than their default scoring functions expose, but that other methods can nonetheless be leveraged.

Related papers

• Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval [25.731213365755234]
  We introduce textitSuperIntelligent Retrieval Agent (SIRA)<n>SIRA can compress multi-round exploratory search into a single corpus-discriminative retrieval action.<n>It can exceed substantially more expensive multi-round search while remaining interpretable, training-free, and efficient.
  arXiv  Detail & Related papers  (2026-05-07T17:54:29Z)
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction [127.64173950476702]
  We study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools.<n>This approach requires no offline indexing and adapts naturally to evolving local corpora.<n>Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines.
  arXiv  Detail & Related papers  (2026-05-03T19:13:11Z)
• Dense X Retrieval: What Retrieval Granularity Should We Use? [56.90827473115201]
  Often-overlooked design choice is the retrieval unit in which the corpus is indexed, e.g. document, passage, or sentence. We introduce a novel retrieval unit, proposition, for dense retrieval. Experiments reveal that indexing a corpus by fine-grained units such as propositions significantly outperforms passage-level units in retrieval tasks.
  arXiv  Detail & Related papers  (2023-12-11T18:57:35Z)
• Revisiting Sparse Retrieval for Few-shot Entity Linking [33.15662306409253]
  We propose an ELECTRA-based keyword extractor to denoise the mention context and construct a better query expression. For training the extractor, we propose a distant supervision method to automatically generate training data based on overlapping tokens between mention contexts and entity descriptions. Experimental results on the ZESHEL dataset demonstrate that the proposed method outperforms state-of-the-art models by a significant margin across all test domains.
  arXiv  Detail & Related papers  (2023-10-19T03:51:10Z)
• SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval [92.27387459751309]
  We provide SPRINT, a unified Python toolkit for evaluating neural sparse retrieval. We establish strong and reproducible zero-shot sparse retrieval baselines across the well-acknowledged benchmark, BEIR. We show that SPLADEv2 produces sparse representations with a majority of tokens outside of the original query and document.
  arXiv  Detail & Related papers  (2023-07-19T22:48:02Z)
• Large Language Models are Strong Zero-Shot Retriever [89.16756291653371]
  We propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, the Language language model as Retriever (LameR), is built upon no other neural models but an LLM.
  arXiv  Detail & Related papers  (2023-04-27T14:45:55Z)
• Bridging the Training-Inference Gap for Dense Phrase Retrieval [104.4836127502683]
  Building dense retrievers requires a series of standard procedures, including training and validating neural models. In this paper, we explore how the gap between training and inference in dense retrieval can be reduced. We propose an efficient way of validating dense retrievers using a small subset of the entire corpus.
  arXiv  Detail & Related papers  (2022-10-25T00:53:06Z)
• Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? [15.618287626892174]
  We introduce the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. In particular, we show that a dense retriever Lambda can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with Lambda.
  arXiv  Detail & Related papers  (2021-10-13T17:56:19Z)
• Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering [87.32442219333046]
  We propose a simple and resource-efficient method to pretrain the paragraph encoder. Our method outperforms an existing dense retrieval method that uses 7 times more computational resources for pretraining.
  arXiv  Detail & Related papers  (2020-04-30T18:09:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.