@inproceedings{qian-etal-2024-large-language,
    title = "Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?",
    author = "Qian, Shenbin  and
      Orasan, Constantin  and
      Kanojia, Diptesh  and
      Do Carmo, F{\'e}lix",
    editor = "Nakazawa, Toshiaki  and
      Goto, Isao",
    booktitle = "Proceedings of the Eleventh Workshop on Asian Translation (WAT 2024)",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2024.wat-1.4/",
    doi = "10.18653/v1/2024.wat-1.4",
    pages = "45--55",
    abstract = "This paper investigates whether large language models (LLMs) are state-of-the-art quality estimators for machine translation of user-generated content (UGC) that contains emotional expressions, without the use of reference translations. To achieve this, we employ an existing emotion-related dataset with human-annotated errors and calculate quality evaluation scores based on the Multi-dimensional Quality Metrics. We compare the accuracy of several LLMs with that of our fine-tuned baseline models, under in-context learning and parameter-efficient fine-tuning (PEFT) scenarios. We find that PEFT of LLMs leads to better performance in score prediction with human interpretable explanations than fine-tuned models. However, a manual analysis of LLM outputs reveals that they still have problems such as refusal to reply to a prompt and unstable output while evaluating machine translation of UGC."
}