English
Related papers

Related papers: Rethinking Chunk Size For Long-Document Retrieval:…

200 papers

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation…

Computation and Language · Computer Science 2025-05-27 Jihao Zhao , Zhiyuan Ji , Zhaoxin Fan , Hanyu Wang , Simin Niu , Bo Tang , Feiyu Xiong , Zhiyu Li

Tabular documents such as CSV and Excel files are widely used in enterprise data pipelines, yet existing chunking strategies for retrieval-augmented generation (RAG) are primarily designed for unstructured text and do not account for…

Computation and Language · Computer Science 2026-05-04 Pooja Guttal , Varun Magotra , Vasudeva Mahavishnu , Natasha Chanto , Sidharth Sivaprasad , Manas Gaur

Retrieval-Augmented Generation (RAG) struggles on long, structured financial filings where relevant evidence is sparse and cross-referenced. This paper presents a systematic investigation of advanced metadata-driven Retrieval-Augmented…

Information Retrieval · Computer Science 2025-10-29 Michail Dadopoulos , Anestis Ladas , Stratos Moschidis , Ioannis Negkakis

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are…

Computation and Language · Computer Science 2025-07-17 Chandana Cheerla

Retrieval-Augmented Generation (RAG) systems have revolutionized information retrieval and question answering, but traditional text-based chunking methods struggle with complex document structures, multi-page tables, embedded figures, and…

Machine Learning · Computer Science 2025-07-15 Vishesh Tripathi , Tanmay Odapally , Indraneel Das , Uday Allu , Biddwan Ahmed

Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk…

Information Retrieval · Computer Science 2026-01-21 Raquib Bin Yousuf , Shengzhe Xu , Mandar Sharma , Andrew Neeser , Chris Latimer , Naren Ramakrishnan

Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into fixed-length chunks. However, fixed truncation risks…

Computation and Language · Computer Science 2025-06-04 Boheng Sheng , Jiacheng Yao , Meicong Zhang , Guoxiu He

Retrieval-augmented generation is increasingly used for financial question answering over long regulatory filings, yet reliability depends on retrieving the exact context needed to justify answers in high stakes settings. We study a…

Computation and Language · Computer Science 2026-02-23 Amine Kobeissi , Philippe Langlais

RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect complex and long industrial document structures, causing information loss and reduced…

Artificial Intelligence · Computer Science 2026-04-15 Joongmin Shin , Chanjun Park , Jeongbae Park , Jaehyung Seo , Heuiseok Lim

Retrieval-augmented generation (RAG) methods can enhance the performance of LLMs by incorporating retrieved knowledge chunks into the generation process. In general, the retrieval and generation steps usually have different requirements for…

Information Retrieval · Computer Science 2025-04-16 Peiru Yang , Xintian Li , Zhiyang Hu , Jiapeng Wang , Jinhua Yin , Huili Wang , Lizhi He , Shuai Yang , Shangguang Wang , Yongfeng Huang , Tao Qi

Dense retrieval systems have proven to be effective across various benchmarks, but require substantial memory to store large search indices. Recent advances in embedding compression show that index sizes can be greatly reduced with minimal…

Information Retrieval · Computer Science 2026-01-16 L. Caspari , M. Dinzinger , K. Ghosh Dastidar , C. Fellicious , J. Mitrović , M. Granitzer

This paper introduces SemRAG, an enhanced Retrieval Augmented Generation (RAG) framework that efficiently integrates domain-specific knowledge using semantic chunking and knowledge graphs without extensive fine-tuning. Integrating…

Computation and Language · Computer Science 2025-07-30 Kezhen Zhong , Basem Suleiman , Abdelkarim Erradi , Shijing Chen

Large Language Models (LLMs) have demonstrated impressive ability in generation and reasoning tasks but struggle with handling up-to-date knowledge, leading to inaccuracies or hallucinations. Retrieval-Augmented Generation (RAG) mitigates…

Databases · Computer Science 2026-03-13 Ziting Wang , Haitao Yuan , Wei Dong , Gao Cong , Feifei Li

Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual…

Computation and Language · Computer Science 2026-04-22 Junjie Wu , Jiangnan Li , Yuqing Li , Lemao Liu , Liyan Xu , Jiwei Li , Dit-Yan Yeung , Jie Zhou , Mo Yu

Retrieval-Augmented Generation (RAG) has become essential for large-scale code generation, grounding predictions in external code corpora to improve actuality. However, a critical yet underexplored aspect of RAG pipelines is chunking -- the…

Software Engineering · Computer Science 2025-10-06 Yilin Zhang , Xinran Zhao , Zora Zhiruo Wang , Chenyang Yang , Jiayi Wei , Tongshuang Wu

Chunking data is obviously no new concept; however, I had never found any data structures that used chunking as the basis of their implementation. I figured that by using chunking alongside concurrency, I could create an extremely fast…

Data Structures and Algorithms · Computer Science 2022-02-21 Daniel Szelogowski

Retrieval-Augmented Generation (RAG) systems have become pivotal in leveraging vast corpora to generate informed and contextually relevant responses, notably reducing hallucinations in Large Language Models. Despite significant…

Computation and Language · Computer Science 2024-12-23 Aakash Mahalingam , Vinesh Kumar Gande , Aman Chadha , Vinija Jain , Divya Chaudhary

Dividing sentences in chunks of words is a useful preprocessing step for parsing, information extraction and information retrieval. (Ramshaw and Marcus, 1995) have introduced a "convenient" data representation for chunking by converting it…

Computation and Language · Computer Science 2007-05-23 Erik F. Tjong Kim Sang , Jorn Veenstra

Integrating Retrieval Augmented Generation (RAG) with Large Language Models (LLMs) has shown the potential to provide precise, contextually relevant responses in knowledge intensive domains. This study investigates the ap-plication of RAG…

Artificial Intelligence · Computer Science 2025-05-26 Salahuddin Alawadhi , Noorhan Abbas

Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful information used to facilitate the generation modules…

Information Retrieval · Computer Science 2025-02-18 Xinping Zhao , Yan Zhong , Zetian Sun , Xinshuo Hu , Zhenyu Liu , Dongfang Li , Baotian Hu , Min Zhang