Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Peiyi, Zhang, Yazhou, Wang, Bo, Rong, Lu, Tiwari, Prayag, Qin, Jing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915881913679872
author Zhang, Peiyi
Zhang, Yazhou
Wang, Bo
Rong, Lu
Tiwari, Prayag
Qin, Jing
author_facet Zhang, Peiyi
Zhang, Yazhou
Wang, Bo
Rong, Lu
Tiwari, Prayag
Qin, Jing
contents In this paper, we present Edu-Values, the first Chinese education values evaluation benchmark that includes seven core values: professional philosophy, teachers' professional ethics, education laws and regulations, cultural literacy, educational knowledge and skills, basic competencies and subject knowledge. We meticulously design 1,418 questions, covering multiple-choice, multi-modal question answering, subjective analysis, adversarial prompts, and Chinese traditional culture (short answer) questions. We conduct human feedback based automatic evaluation over 21 state-of-the-art (SoTA) LLMs, and highlight three main findings: (1) due to differences in educational culture, Chinese LLMs outperform English LLMs, with Qwen 2 ranking the first with a score of 81.37; (2) LLMs often struggle with teachers' professional ethics and professional philosophy; (3) leveraging Edu-Values to build an external knowledge repository for RAG significantly improves LLMs' alignment. This demonstrates the effectiveness of the proposed benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12739
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models
Zhang, Peiyi
Zhang, Yazhou
Wang, Bo
Rong, Lu
Tiwari, Prayag
Qin, Jing
Computation and Language
In this paper, we present Edu-Values, the first Chinese education values evaluation benchmark that includes seven core values: professional philosophy, teachers' professional ethics, education laws and regulations, cultural literacy, educational knowledge and skills, basic competencies and subject knowledge. We meticulously design 1,418 questions, covering multiple-choice, multi-modal question answering, subjective analysis, adversarial prompts, and Chinese traditional culture (short answer) questions. We conduct human feedback based automatic evaluation over 21 state-of-the-art (SoTA) LLMs, and highlight three main findings: (1) due to differences in educational culture, Chinese LLMs outperform English LLMs, with Qwen 2 ranking the first with a score of 81.37; (2) LLMs often struggle with teachers' professional ethics and professional philosophy; (3) leveraging Edu-Values to build an external knowledge repository for RAG significantly improves LLMs' alignment. This demonstrates the effectiveness of the proposed benchmark.
title Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2409.12739