Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Miao, Chen, Ming-Bin, Tang, Bo, Hou, Shengbin, Wang, Pengyu, Deng, Haiying, Li, Zhiyu, Xiong, Feiyu, Mao, Keming, Cheng, Peng, Luo, Yi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.00862
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911903050104832
author Li, Miao
Chen, Ming-Bin
Tang, Bo
Hou, Shengbin
Wang, Pengyu
Deng, Haiying
Li, Zhiyu
Xiong, Feiyu
Mao, Keming
Cheng, Peng
Luo, Yi
author_facet Li, Miao
Chen, Ming-Bin
Tang, Bo
Hou, Shengbin
Wang, Pengyu
Deng, Haiying
Li, Zhiyu
Xiong, Feiyu
Mao, Keming
Cheng, Peng
Luo, Yi
contents We present NewsBench, a novel evaluation framework to systematically assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. Our constructed benchmark dataset is focused on four facets of writing proficiency and six facets of safety adherence, and it comprises manually and carefully designed 1,267 test samples in the types of multiple choice questions and short answer questions for five editorial tasks in 24 news domains. To measure performances, we propose different GPT-4 based automatic evaluation protocols to assess LLM generations for short answer questions in terms of writing proficiency and safety adherence, and both are validated by the high correlations with human evaluations. Based on the systematic evaluation framework, we conduct a comprehensive analysis of ten popular LLMs which can handle Chinese. The experimental results highlight GPT-4 and ERNIE Bot as top performers, yet reveal a relative deficiency in journalistic safety adherence in creative writing tasks. Our findings also underscore the need for enhanced ethical guidance in machine-generated journalistic content, marking a step forward in aligning LLMs with journalistic standards and safety considerations.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00862
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism
Li, Miao
Chen, Ming-Bin
Tang, Bo
Hou, Shengbin
Wang, Pengyu
Deng, Haiying
Li, Zhiyu
Xiong, Feiyu
Mao, Keming
Cheng, Peng
Luo, Yi
Computation and Language
Artificial Intelligence
We present NewsBench, a novel evaluation framework to systematically assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. Our constructed benchmark dataset is focused on four facets of writing proficiency and six facets of safety adherence, and it comprises manually and carefully designed 1,267 test samples in the types of multiple choice questions and short answer questions for five editorial tasks in 24 news domains. To measure performances, we propose different GPT-4 based automatic evaluation protocols to assess LLM generations for short answer questions in terms of writing proficiency and safety adherence, and both are validated by the high correlations with human evaluations. Based on the systematic evaluation framework, we conduct a comprehensive analysis of ten popular LLMs which can handle Chinese. The experimental results highlight GPT-4 and ERNIE Bot as top performers, yet reveal a relative deficiency in journalistic safety adherence in creative writing tasks. Our findings also underscore the need for enhanced ethical guidance in machine-generated journalistic content, marking a step forward in aligning LLMs with journalistic standards and safety considerations.
title NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2403.00862