MYMu You

Mu You

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mu You has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Masked Cloze Scoring (MCS): Zero-Shot Automated Essay Scoring via Masked Predictions from Large Language Models

    by Jiaxu Zuo, Mu You, Kaixin Lan, Tao Fang, Jing Zhang, Lidia S. Chao, Derek F. Wong

    Traditional Automated Essay Scoring (AES) methods typically require large amounts of labeled data and extensive model training. Recent advances in Large Language Models (LLMs) have enabled zero-shot AES methods that bypass these requirements. In this paper, we propose Masked Cloze Scoring (MCS), a novel zero-shot method that leverages LLMs’ masked language modeling capacity as its core mechanism for evaluating how well an essay aligns with model predictions. Unlike prior methods that prompt LLMs to assign scores directly, MCS integrates two complementary signals: in-context word prediction for micro-level lexical appropriateness, and relative essay length as a proxy for macro-level writing quality. Experimental results demonstrate that MCS consistently outperforms existing training-free zero-shot baselines on two widely used benchmark datasets, ASAP and TOEFL11. Compared with LCES, the state-of-the-art zero-shot method that requires additional training, MCS underperforms on TOEFL11 but achieves comparable performance on ASAP. Moreover, MCS attains performance comparable to that of three strong supervised cross-prompt baselines on ASAP. Beyond holistic scoring, MCS produces word-level diagnostic feedback, offering added pedagogical benefits. Overall, MCS advances the state of training-free zero-shot AES, delivering competitive performance without requiring labeled data or additional training.

  • Open Access

    Exploring learner prompting and AI feedback quality in L2 Portuguese writing

    by Mu You, Jing Zhang, Chunhui Lu, Ana Cristina Ferreira de Almeida Rodrigues Alves, Jiaxu Zuo

    For L2 Portuguese learners in Macau, artificial intelligence (AI) has become a primary source of immediate writing feedback for Chinese university students. This study investigates authentic learner prompting practices and the accuracy of resulting AI-generated revisions in L2 Portuguese writing. Forty-six second-year Portuguese Studies majors, divided into a control condition and a justification condition that required them to rationalize every modification, revised a first-year learner composition using their preferred AI tools. Results reveal that students predominantly prompted in Chinese, employed highly anthropomorphic and polite language, relied on generic or grammar-focused requests, and frequently exhibited misalignment between intended goals and actual prompts. The requirement to justify revisions increased interaction turns and shifted attention toward smaller textual units and explanation-seeking, though it also produced higher error rates in the resulting revisions. Experiments with researcher-designed prompts demonstrated the potential of simple prompt engineering strategies, with the Rephrase-and-Respond technique eliciting the most accurate revisions. The findings underscore the immaturity of untrained prompting, the context-sensitive nature of prompt engineering, and the practical pedagogical value of current LLMs even under naïve use. To foster critical and reflective human-AI collaboration in L2 writing, pedagogical interventions such as explicit instruction in prompting strategies and the use of tasks that require justification or explanation-seeking are recommended.

  • Open Access

    How well can state-of-the-art machine translation systems render a 16th-century Chinese novel?

    by Mu You, Derek F. Wong, Jing Zhang, Kaixin Lan

    This study evaluates the performance of state-of-the-art machine translation systems in rendering Journey to the West, a culturally rich 16th-century Chinese novel, into Portuguese. Employing a mixed-methods approach, we compare translations produced by DeepSeek-V3, GPT-4o, DeepL Pro, and NovelTrans-J against a published human translation. Quantitative assessments conducted by an expert evaluator examine accuracy, fluency, stylistic elegance, cultural appropriateness, and overall translation quality at both the sentence and chunk levels. The results reveal that three MT systems (DeepSeek-V3, GPT-4o, and NovelTrans-J) produce translations of comparable or superior quality to the human translation. Among them, NovelTrans-J consistently outperforms all other participants, particularly in terms of cultural appropriateness. In contrast, DeepL Pro demonstrates significantly weaker performance across all evaluated dimensions. To complement the quantitative analysis, a qualitative investigation focuses on the rendering of culture-specific items (CSIs). NovelTrans-J exhibits outstanding performance, producing the fewest mistranslations and uniquely providing explanatory notes that facilitate reader comprehension. DeepSeek-V3 and GPT-4o also handle CSIs competently, though with less consistency, while DeepL Pro struggles considerably, showing a high rate of CSI mistranslations and generally low quality. Interestingly, the human translation also contains notable CSI-related errors, particularly in cases involving semantically opaque expressions, an area in which all participants encounter significant difficulty. These findings underscore the growing potential of MT systems to handle complex, culturally rich literary texts, although certain challenges, such as the translation of semantically opaque expressions, remain significant obstacles. We hope this study provides an updated perspective on the current capabilities of MT and offers practical insights to guide the development of future systems that can more accurately capture and transmit the distinctive cultural nuances embedded in literary works.


  • Open Access

    Umplc: the first longitudinal learner corpus of Portuguese

    by Mu You, Jing Zhang, Derek F. Wong, Kaixin Lan


  • Open Access

    Corpus de aprendizes de português da Universidade de Macau e ensino de português L2

    by Jing Zhang, Mu You

    O presente artigo apresenta um corpus de aprendizes chineses de português L2 com a anotação de PoS e lema, destacando-se sua potencialidade de análise quantitativa e qualitativa na identificação de padrões linguísticos dos aprendizes, contribuindo, dessa forma, para o ensino de português L2. Este corpus (Corpus de Aprendizes de Português da Universidade de Macau), denominado UMPLC, contém, no total, 933 composições produzidas por 122 estudantes de português da Universidade de Macau durante três anos de estudo consecutivos. A anotação de PoS e lema realizou-se através do Stanza, anotador automático desenvolvido por Qi et al. ( 2020 QI, Peng; ZHANG, Yuhao; ZHANG, Yuhui; BOLTON, Jason; MANNING, Christopher D. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. In: PROCEEDINGS of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. [S. l.: s. n.], 2020. Disponível em: https://nlp.stanford.edu/pubs/qi2020stanza.pdf . https://nlp.stanford.edu/pubs/qi2020stan... ). A fim de garantir a consistência de anotação, o resultado foi revisado manualmente. Nesta pesquisa, as informações de PoS e lema permitem-nos investigar quantitativa e qualitativamente diversos fenômenos existentes no corpus relativos ao aspeto lexical e à mudança diacrônica desse aspeto. Dois estudos foram realizados com base em uma abordagem contrastiva, comparando-se o português dos aprendizes do corpus com o português nativo. Foram descobertas características de não-natividade linguística desses aprendizes, o que permitirá que os professores de português L2 se concentrem nas áreas em que é necessário um trabalho corretivo.