@inproceedings{utama-etal-2026-cross,
    title = "Cross-Lingual Emotion Recognition in {B}alinese Text using Multilingual-{LLM}s under Peer-Collaborations Settings",
    author = "Utama, Putu Kussa Laksana  and
      Tashu, Tsegaye Misikir  and
      Dibangoye, Jilles Steeve",
    editor = "Hettiarachchi, Hansi  and
      Ranasinghe, Tharindu  and
      Plum, Alistair  and
      Rayson, Paul  and
      Mitkov, Ruslan  and
      Gaber, Mohamed  and
      Premasiri, Damith  and
      Tan, Fiona Anting  and
      Uyangodage, Lasitha",
    booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.loreslm-1.21/",
    pages = "225--238",
    ISBN = "979-8-89176-377-7",
    abstract = "Cross-Lingual Emotion Recognition (CLER) remains a formidable challenge for ultra-low-resource languages like Balinese due to the scarcity of high-quality annotated data and the performance limitations of traditional multilingual models. This study addresses these gaps through two primary contributions. First, we present a newly created multi-label Balinese emotion dataset annotated by a panel of experts in Balinese linguistics and psychology. Second, we propose the Multi-Agent Peer Collaboration (MAPC) framework, which transforms the multi-label classification problem into a series of independent binary tasks to leverage the collaborative reasoning of Large Language Models (LLMs). We evaluated the framework against the LaBSE multilingual model and three LLMs of varying scales under zero-shot and few-shot settings using the Macro-F1 measure. The experimental results showed that LLMs significantly outperform traditional Pre-trained Language Models (PLMs). MAPC achieved an overall macro $F_1$-score of 63.95, which was higher than the individual baselines in both zero-shot and few-shot settings. Analysis shows that while some models exhibit sensitivity to few-shot prompting in low-resource contexts, the MAPC review and revision process consistently improves individual reasoning and provides a more accurate final classification."
}