English
Related papers

Related papers: Query Embedding Pruning for Dense Retrieval

200 papers

Reranking, the process of refining the output from a first-stage retriever, is often considered computationally expensive, especially when using Large Language Models (LLMs). A common approach to mitigate this cost involves utilizing…

Information Retrieval · Computer Science 2026-04-30 Hervé Déjean , Stéphane Clinchant

In the field of multi-document summarization (MDS), transformer-based models have demonstrated remarkable success, yet they suffer an input length limitation. Current methods apply truncation after the retrieval process to fit the context…

Machine Learning · Computer Science 2025-04-24 Shiyin Tan , Jaeeon Park , Dongyuan Li , Renhe Jiang , Manabu Okumura

Large Language Models (LLMs) have recently demonstrated strong capabilities in tool use, yet progress in tool retrieval remains hindered by incomplete and heterogeneous tool documentation. To address this challenge, we introduce Tool-DE, a…

Information Retrieval · Computer Science 2025-10-28 Xuan Lu , Haohang Huang , Rui Meng , Yaohui Jin , Wenjun Zeng , Xiaoyu Shen

Vector embeddings have been tasked with an ever-increasing set of retrieval tasks over the years, with a nascent rise in using them for reasoning, instruction-following, coding, and more. These new benchmarks push embeddings to work for any…

Information Retrieval · Computer Science 2026-03-13 Orion Weller , Michael Boratko , Iftekhar Naim , Jinhyuk Lee

Dense retrieval is becoming one of the standard approaches for document and passage ranking. The dual-encoder architecture is widely adopted for scoring question-passage pairs due to its efficiency and high performance. Typically, dense…

Information Retrieval · Computer Science 2022-05-06 Georgios Sidiropoulos , Evangelos Kanoulas

The advent of transformer-based models such as BERT has led to the rise of neural ranking models. These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25. While…

Information Retrieval · Computer Science 2022-01-27 Suraj Nair , Eugene Yang , Dawn Lawrie , Kevin Duh , Paul McNamee , Kenton Murray , James Mayfield , Douglas W. Oard

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…

Computation and Language · Computer Science 2023-11-28 Timo Kats , Peter van der Putten , Jan Scholtes

Multi-vector late-interaction retrievers such as ColBERT achieve state-of-the-art retrieval quality, but their query-time cost is dominated by exhaustively computing token-level MaxSim interactions for every candidate document. While…

Information Retrieval · Computer Science 2026-02-04 Roi Pony , Adi Raz , Oshri Naparstek , Idan Friedman , Udi Barzelay

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Computation and Language · Computer Science 2023-10-09 Fangyuan Xu , Weijia Shi , Eunsol Choi

Deep pretrained transformer networks are effective at various ranking tasks, such as question answering and ad-hoc document ranking. However, their computational expenses deem them cost-prohibitive in practice. Our proposed approach, called…

Information Retrieval · Computer Science 2020-05-27 Sean MacAvaney , Franco Maria Nardini , Raffaele Perego , Nicola Tonellotto , Nazli Goharian , Ophir Frieder

In this paper, we present our approaches for the case law retrieval and the legal case entailment task in the Competition on Legal Information Extraction/Entailment (COLIEE) 2021. As first stage retrieval methods combined with neural…

Information Retrieval · Computer Science 2021-08-10 Sophia Althammer , Arian Askari , Suzan Verberne , Allan Hanbury

We present an approach to ranking with dense representations that applies knowledge distillation to improve the recently proposed late-interaction ColBERT model. Specifically, we distill the knowledge from ColBERT's expressive MaxSim…

Information Retrieval · Computer Science 2020-10-23 Sheng-Chieh Lin , Jheng-Hong Yang , Jimmy Lin

Dense retrieval models usually adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model usually…

Information Retrieval · Computer Science 2025-09-30 Zhongbin Xie , Thomas Lukasiewicz

Embedding-based retrieval (EBR) is a technique to use embeddings to represent query and document, and then convert the retrieval problem into a nearest neighbor search problem in the embedding space. Some previous works have mainly focused…

Information Retrieval · Computer Science 2023-05-09 Wenbiao Li , Pan Tang , Zhengfan Wu , Weixue Lu , Minghua Zhang , Zhenlei Tian , Daiting Shi , Yu Sun , Simiu Gu , Dawei Yin

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…

Machine Learning · Computer Science 2026-05-08 Weien Li , Rui Song , Zeyu Li , Haochen Liu , Gonghao Zhang , Difan Jiao , Zhenwei Tang , Bowei He , Haolun Wu , Xue Liu , Ye Yuan

High-dimensional dense embeddings have become central to modern Information Retrieval, but many dimensions are noisy or redundant. Recently proposed DIME (Dimension IMportance Estimation), provides query-dependent scores to identify…

Information Retrieval · Computer Science 2026-04-13 Giulio D'Erasmo , Cesare Campagnano , Antonio Mallia , Pierpaolo Brutti , Nicola Tonellotto , Fabrizio Silvestri

Most text retrievers generate \emph{one} query vector to retrieve relevant documents. Yet, the conditional distribution of relevant documents for the query may be multimodal, e.g., representing different interpretations of the query. We…

Computation and Language · Computer Science 2025-11-05 Hung-Ting Chen , Xiang Liu , Shauli Ravfogel , Eunsol Choi

Dense embedding models have become critical for modern information retrieval, particularly in RAG pipelines, but their performance often degrades when applied to specialized corpora outside their pre-training distribution. To address thi we…

Information Retrieval · Computer Science 2025-10-29 Nathan Paull

With the rapid proliferation of textual data, predicting long texts has emerged as a significant challenge in the domain of natural language processing. Traditional text prediction methods encounter substantial difficulties when grappling…

Computation and Language · Computer Science 2024-01-24 Jiahui Zhao , Ziyi Meng , Stepan Gordeev , Zijie Pan , Dongjin Song , Sandro Steinbach , Caiwen Ding

Dense retrieval systems increasingly need to handle complex queries. In many realistic settings, users express intent through long instructions or task-specific descriptions, while target documents remain relatively simple and static. This…

Information Retrieval · Computer Science 2026-04-07 Seiji Maekawa , Moin Aminnaseri , Pouya Pezeshkpour , Estevam Hruschka