# Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts

Source: [Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-04T05:01:04.042Z

Authors: Valentin J. J. Kreileder, Johannes Reisinger, Andreas Fischer

Published: 2026-07-02T08:12:35.000Z

## Abstract

Retrieval-Augmented Generation (RAG) systems use the question-answering capabilities of Large Language Models (LLMs) to access information outside their parameters. We evaluate if cluster-based semantic chunking improves retrieval and answer quality compared to fixed-size and recursive chunking evaluating on long, structured academic theses using the Retrieval Augmented Generation Assessment (RAGAs) framework. RAGAs based faithfulness shows limited reliability in this setup. Performance on fixed versus document specific questions varied substantially, likely related to the formatting of documents and preprocessing. Under the tested configuration, cluster-based chunking did not outperform simpler strategies.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.01852>)

[PDF](<https://arxiv.org/pdf/2607.01852.pdf>)
