English
Related papers

Related papers: Learning to Tokenize for Generative Retrieval

200 papers

Ever-larger language models with ever-increasing capabilities are by now well-established text processing tools. Alas, information extraction tasks such as named entity recognition are still largely unaffected by this progress as they are…

Computation and Language · Computer Science 2023-08-16 Tobias Deußer , Lars Hillebrand , Christian Bauckhage , Rafet Sifa

Workbook-scale spreadsheet understanding is increasingly important for language-model-based data analysis agents, but remains challenging because relevant information is often distributed across multiple sheets with heterogeneous schemas,…

Artificial Intelligence · Computer Science 2026-05-08 Yiming Lei , Yiqi Wang , Yujia Zhang , Bo Guan , Depei Zhu , Chunhui Wang , Zhuonan Hao , Tianyu Shi

Document categorization, which aims to assign a topic label to each document, plays a fundamental role in a wide variety of applications. Despite the success of existing studies in conventional supervised document classification, they are…

Computation and Language · Computer Science 2023-10-24 Yu Zhang , Yu Meng , Jiaxin Huang , Frank F. Xu , Xuan Wang , Jiawei Han

This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Pramuditha Perera , Matthew Trager , Luca Zancato , Alessandro Achille , Stefano Soatto

Document understanding tasks, in particular, Visually-rich Document Entity Retrieval (VDER), have gained significant attention in recent years thanks to their broad applications in enterprise AI. However, publicly available data have been…

Computation and Language · Computer Science 2023-10-27 Lijun Yu , Jin Miao , Xiaoyu Sun , Jiayi Chen , Alexander G. Hauptmann , Hanjun Dai , Wei Wei

Tokenization is a crucial step in information retrieval, especially for lexical matching algorithms, where the quality of indexable tokens directly impacts the effectiveness of a retrieval system. Since different languages have unique…

Computation and Language · Computer Science 2022-10-12 Odunayo Ogundepo , Xinyu Zhang , Jimmy Lin

We present our method for tackling a legal case retrieval task by introducing our method of encoding documents by summarizing them into continuous vector space via our phrase scoring framework utilizing deep neural networks. On the other…

Computation and Language · Computer Science 2023-09-18 Vu Tran , Minh Le Nguyen , Satoshi Tojo , Ken Satoh

Query auto-completion (QAC) has been widely studied in the context of web search, yet remains underexplored for in-document search, which we term DocQAC. DocQAC aims to enhance search productivity within long documents by helping users…

Information Retrieval · Computer Science 2026-04-21 Rahul Mehta , Kavin R , Indrajit Pal , Tushar Abhishek , Pawan Goyal , Manish Gupta

Retrieval-augmented generation (RAG) is a common way to ground language models in external documents and up-to-date information. Classical retrieval systems relied on lexical methods such as BM25, which rank documents by term overlap with…

Computation and Language · Computer Science 2026-03-05 Martin Asenov , Kenza Benkirane , Dan Goldwater , Aneiss Ghodsi

Legal document retrieval and judgment prediction are crucial tasks in intelligent legal systems. In practice, determining whether two documents share the same judgments is essential for establishing their relevance in legal retrieval.…

Information Retrieval · Computer Science 2024-04-16 Weicong Qin , Zelin Cao , Weijie Yu , Zihua Si , Sirui Chen , Jun Xu

Retrieval-Augmented Generation (RAG) systems depend on the geometric properties of vector representations to retrieve contextually appropriate evidence. When source documents interleave multiple topics within contiguous text, standard…

Artificial Intelligence · Computer Science 2026-04-21 Nick Loghmani

According to common relevance-judgments regimes, such as TREC's, a document can be deemed relevant to a query even if it contains a very short passage of text with pertinent information. This fact has motivated work on passage-based…

Information Retrieval · Computer Science 2019-06-06 Eilon Sheetrit , Anna Shtok , Oren Kurland

Generative retrieval models encode pointers to information in a corpus as an index within the model's parameters. These models serve as part of a larger pipeline, where retrieved information conditions generation for knowledge-intensive NLP…

Information Retrieval · Computer Science 2024-02-26 EuiYul Song , Sangryul Kim , Haeju Lee , Joonkee Kim , James Thorne

Vision-language models (VLMs) have shown strong performance on text-to-image retrieval benchmarks. However, bridging this success to real-world applications remains a challenge. In practice, human search behavior is rarely a one-shot…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Diji Yang , Minghao Liu , Chung-Hsiang Lo , Yi Zhang , James Davis

An emerging recipe for achieving state-of-the-art effectiveness in neural document re-ranking involves utilizing large pre-trained language models - e.g., BERT - to evaluate all individual passages in the document and then aggregating the…

Information Retrieval · Computer Science 2021-05-21 Sebastian Hofstätter , Bhaskar Mitra , Hamed Zamani , Nick Craswell , Allan Hanbury

Text-to-image retrieval is a fundamental task in multimedia processing, aiming to retrieve semantically relevant cross-modal content. Traditional studies have typically approached this task as a discriminative problem, matching the text and…

Multimedia · Computer Science 2024-07-25 Yongqi Li , Hongru Cai , Wenjie Wang , Leigang Qu , Yinwei Wei , Wenjie Li , Liqiang Nie , Tat-Seng Chua

Leveraging Large Language Models (LLMs) for generative recommendation has attracted significant research interest, where item tokenization is a critical step. It involves assigning item identifiers for LLMs to encode user history and…

Information Retrieval · Computer Science 2025-05-27 Xinyu Lin , Haihan Shi , Wenjie Wang , Fuli Feng , Qifan Wang , See-Kiong Ng , Tat-Seng Chua

A limitation of modern document retrieval embedding methods is that they typically encode passages (chunks) from the same documents independently, often overlooking crucial contextual information from the rest of the document that could…

Information Retrieval · Computer Science 2025-06-09 Max Conti , Manuel Faysse , Gautier Viaud , Antoine Bosselut , Céline Hudelot , Pierre Colombo

Recent advancements in autoregressive and diffusion models have led to strong performance in image generation with short scene text words. However, generating coherent, long-form text in images, such as paragraphs in slides or documents,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Alex Jinpeng Wang , Linjie Li , Zhengyuan Yang , Lijuan Wang , Min Li

Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic…

Information Retrieval · Computer Science 2019-05-24 Tolgahan Cakaloglu , Xiaowei Xu