notesum.ai

Published at November 21

Benchmarking GPT-4 against Human Translators: A Comprehensive Evaluation Across Languages, Domains, and Expertise Levels

cs.CL

cs.AI

Released Date: November 21, 2024

Authors: Jianhao Yan, Pingchuan Yan, Yulong Chen, Jing Li, Xianchao Zhu, Yue Zhang

Arxiv: http://arxiv.org/abs/2411.13775v1

Refer to caption

		Severity		Error Type
Translator		Minor	Major	Accuracy	Fluency
	Seamless	29.52	17.35	28.25	17.37
Machine	GPT4	20.43	03.71	11.12	12.95
	Junior	18.19	03.27	08.55	12.74
	Medium	20.19	03.30	12.58	10.66
Human	Senior	12.04	01.83	07.93	05.93