Saved in:
Bibliographic Details
Main Authors: Lee, Hung-Shin, Chang, Chen-Chi, Chen, Ching-Yuan, Hsu, Yun-Hsiang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.01649
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918183748763648
author Lee, Hung-Shin
Chang, Chen-Chi
Chen, Ching-Yuan
Hsu, Yun-Hsiang
author_facet Lee, Hung-Shin
Chang, Chen-Chi
Chen, Ching-Yuan
Hsu, Yun-Hsiang
contents This study proposes a cognitive benchmarking framework to evaluate how large language models (LLMs) process and apply culturally specific knowledge. The framework integrates Bloom's Taxonomy with Retrieval-Augmented Generation (RAG) to assess model performance across six hierarchical cognitive domains: Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating. Using a curated Taiwanese Hakka digital cultural archive as the primary testbed, the evaluation measures LLM-generated responses' semantic accuracy and cultural relevance.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01649
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Cultural Knowledge Processing in Large Language Models: A Cognitive Benchmarking Framework Integrating Retrieval-Augmented Generation
Lee, Hung-Shin
Chang, Chen-Chi
Chen, Ching-Yuan
Hsu, Yun-Hsiang
Computation and Language
This study proposes a cognitive benchmarking framework to evaluate how large language models (LLMs) process and apply culturally specific knowledge. The framework integrates Bloom's Taxonomy with Retrieval-Augmented Generation (RAG) to assess model performance across six hierarchical cognitive domains: Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating. Using a curated Taiwanese Hakka digital cultural archive as the primary testbed, the evaluation measures LLM-generated responses' semantic accuracy and cultural relevance.
title Evaluating Cultural Knowledge Processing in Large Language Models: A Cognitive Benchmarking Framework Integrating Retrieval-Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2511.01649