# Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion

arXiv: https://arxiv.org/abs/2108.08513 · HTML: https://mlsanity.com/paper/2108.08513/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2021.

## Built on by (most cited first, 20 of 20)

- [Searching for Best Practices in Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01219/) (2024)
- [Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely](https://mlsanity.com/paper/2409.14924/) (2024)
- [Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation](https://mlsanity.com/paper/2206.10128/) (2022)
- [Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking](https://mlsanity.com/paper/2310.13243/) (2023)
- [An Efficiency Study for SPLADE Models](https://mlsanity.com/paper/2207.03834/) (2022)
- [A Proposed Conceptual Framework for a Representational Approach to Information Retrieval](https://mlsanity.com/paper/2110.01529/) (2021)
- [Evaluating Generative Ad Hoc Information Retrieval](https://mlsanity.com/paper/2311.04694/) (2023)
- [Enhancing Lexicon-Based Text Embeddings with Large Language Models](https://mlsanity.com/paper/2501.09749/) (2025)
- [Sparsifying Sparse Representations for Passage Retrieval by Top-k Masking](https://mlsanity.com/paper/2112.09628/) (2021)
- [Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval](https://mlsanity.com/paper/2205.11498/) (2022)
- [Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval](https://mlsanity.com/paper/2304.01019/) (2023)
- [NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders](https://mlsanity.com/paper/2305.14499/) (2023)
- [SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval](https://mlsanity.com/paper/2307.10488/) (2023)
- [ENCO: Life-Cycle Management of Enterprise-Grade Copilots](https://mlsanity.com/paper/2412.06099/) (2024)
- [Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues](https://mlsanity.com/paper/2204.10558/) (2022)
- [FecTek: Enhancing Term Weight in Lexicon-Based Retrieval with Feature Context and Term-level Knowledge](https://mlsanity.com/paper/2404.12152/) (2024)
- [Semi-Parametric Retrieval via Binary Bag-of-Tokens Index](https://mlsanity.com/paper/2405.01924/) (2024)
- [HyReC: Exploring Hybrid-based Retriever for Chinese](https://mlsanity.com/paper/2506.21913/) (2025)
- [GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search](https://mlsanity.com/paper/2602.15423/) (2026)
- [An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case](https://mlsanity.com/paper/2608.14587/) (2026)

## Abstract (arXiv)

BERT-based information retrieval models are expensive, in both time (query latency) and computational resources (energy, hardware cost), making many of these models impractical especially under resource constraints. The reliance on a query encoder that only performs tokenization and on the pre-processing of passage representations at indexing, has allowed the recently proposed TILDE method to overcome the high query latency issue typical of BERT-based models. This however is at the expense of a lower effectiveness compared to other BERT-based re-rankers and dense retrievers. In addition, the original TILDE method is characterised by indexes with a very high memory footprint, as it expands each passage into the size of the BERT vocabulary. In this paper, we propose TILDEv2, a new model that stems from the original TILDE but that addresses its limitations. TILDEv2 relies on contextualized exact term matching with expanded passages. This requires to only store in the index the score of tokens that appear in the expanded passages (rather than all the vocabulary), thus producing indexes that are 99% smaller than those of TILDE. This matching mechanism also improves ranking effectiveness by 24%, without adding to the query latency. This makes TILDEv2 the state-of-the-art passage re-ranking method for CPU-only environments, capable of maintaining query latency below 100ms on commodity hardware.