Year: 2025
Type: article
Abstract: Retrieval Augmented Generation (RAG) combines chunks of documents with a prompt to be analyzed by an LLM, enhancing the response's quality and reducing the risk of hallucinations.Existing chunking methods divides the text into chunks of predetermined length (fixed-size strategy), segments text at punctuation marks (recursive strategy), or aims at capturing the core meaning within each segment (semantic strategy).All these strategies limit context accessibility and encounter information loss, especially with larger documents and multi-layered information.They often require post-processing steps to avoid omitting crucial information, especially toward the documents' end.This paper introduces a paragraph-based chunking strategy that can benefit from larger context blocks.The proposed strategy leverages document structure metadata, such as font size and text formatting, to generate more semantically coherent chunks.The approach has been evaluated using both automated and empirical methods, exploiting standard metrics.The results demonstrate a promising enhancement for RAG applications, facilitating more effective document comprehension and improving context utilization in LLM-driven tasks compared to existing strategies.
Institution: University of Sannio
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4415441928