{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T02:07:44Z","timestamp":1772935664999,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402402","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"2513-2518","source":"Crossref","is-referenced-by-count":0,"title":["Mix-Of-Overlap: Enhancing Retrieval-Augmented Generation with Multi-Overlap Chunking"],"prefix":"10.1109","author":[{"given":"Mahdi Ben","family":"Ameur","sequence":"first","affiliation":[{"name":"Proxym-Group"}]},{"given":"Mohamed Ali","family":"Fathallah","sequence":"additional","affiliation":[{"name":"Proxym-Group"}]},{"given":"Takoua","family":"Abdellatif","sequence":"additional","affiliation":[{"name":"Proxym-Group"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Retrieval-Augmented Generation for KnowledgeIntensive NLP","author":"Lewis","year":"2020","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Financial Report Chunking for Effective Retrieval Augmented Generation","volume-title":"arXiv","author":"Jimeno-Yepes","year":"2024"},{"key":"ref3","year":"2024","journal-title":"Text Splitting Chunking: Fixed windows and overlaps"},{"key":"ref4","article-title":"Enhancing QA Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG","author":"De Souza","year":"2024","journal-title":"arXiv"},{"key":"ref5","author":"Islam","year":"2023","journal-title":"FinanceBench: A New Benchmark for Financial Question Answering"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref7","year":"2024","journal-title":"Text Splitters: Recursive character and fixed-size policies"},{"key":"ref8","article-title":"TextTiling: Segmenting Text into Multi-paragraph Subtopic Passages","author":"Hearst","year":"1997","journal-title":"Computational Linguistics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"ref10","article-title":"DocLayNet: A Large Human-annotated Dataset for Document-Layout Understanding","year":"2022","journal-title":"arXiv"},{"key":"ref11","year":"2024","journal-title":"Partitioning PDFs, OCR and element extraction"},{"key":"ref12","article-title":"Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation","author":"Zhong","year":"2024","journal-title":"arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761587"},{"key":"ref14","article-title":"RPO: Retrieval Preference Optimization for Robust RAG","author":"Yan","year":"2025","journal-title":"arXiv"},{"key":"ref15","article-title":"RAG-Reward: Optimizing RAG with Reward Modeling and RLHF","author":"Zhang","year":"2025","journal-title":"arXiv"},{"key":"ref16","article-title":"LongRAG: Enhancing RetrievalAugmented Generation with Long-context LLMs","author":"Jiang","year":"2024","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5121\/ijnlc.2024.13103"},{"key":"ref18","article-title":"The TREC-8 Question Answering Track Report","volume-title":"Proceedings of the 8th Text Retrieval Conference (TREC-8)","author":"Voorhees"},{"key":"ref19","article-title":"multi-qa-mpnet-base-dot-v1 (model card)","year":"2021","journal-title":"Hugging Face"},{"key":"ref20","article-title":"BAAI\/bge-reranker-base (model card)","year":"2025","journal-title":"Hugging Face"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402402.pdf?arnumber=11402402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:37:53Z","timestamp":1772869073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402402","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}