The Effect of Chunk Size on the RAG Performance
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F25%3A50022585" target="_blank" >RIV/62690094:18450/25:50022585 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-032-00712-4_21" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-032-00712-4_21</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-032-00712-4_21" target="_blank" >10.1007/978-3-032-00712-4_21</a>
Alternative languages
Result language
angličtina
Original language name
The Effect of Chunk Size on the RAG Performance
Original language description
Retrieval-Augmented Generation (RAG) is an emerging paradigm that enhances the performance of Large Language Models (LLMs) by integrating external knowledge retrieval into their generative processes. One of the key challenges in optimizing RAG systems is the selection of an appropriate retrieval dataset, which directly affects model accuracy, retrieval efficiency, and response coherence. The chunk size plays a fundamental role in the performance of RAG systems, as it directly impacts retrieval efficiency, response quality, and computational costs. The Neural Bridge RAG Dataset 12000 was used to test the effect of a chunk size in our experiment.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Lecture Notes in Networks and Systems
ISBN
978-3-032-00711-7
ISSN
2367-3370
e-ISSN
2367-3389
Number of pages
10
Pages from-to
317-326
Publisher name
Springer
Place of publication
Cham
Event location
Moscow
Event date
Apr 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—