【摘要】 本研究使用生成式人工智能工具ChatGPT基于新修订《中国英语能力等级量表》(CSE)生成的分项评分量表，引入ChatGPT作为评分员和人工评分员共同评价笔译能力，并运用多层面Rasch模型对基于分项评分量表的人工评分与人工智能评分开展效度验证。研究发现，ChatGPT经训练后可依据分项评分量表对译文进行有效评分，且与人工评分的一致性较高。ChatGPT赋能的CSE在翻译教学评价中的应用具有一定可行性。更多还原

【Abstract】 This study employs an analytical rating scale generated by the generative artificial intelligence tool ChatGPT based on the updated China’s Standards of English Language Ability(CSE), incorporates ChatGPT as a rater and human raters in assessing translation competence, and validates the manual scoring and AI-based asessment by the Multi-Facets Rasch Model. The findings indicate that ChatGPT can be effectively trained to assess translations using the analytical rating scale and has demonstrated a high level of agreement with human raters. Hence the application of the CSE empowered by ChatGPT in translation teaching assessment appears to be a viable option.更多还原