@inproceedings{akarajaradwong-etal-2025-aligning,
    title = "Aligning {LLM}s for {T}hai Legal Question Answering with Efficient Semantic-Similarity Rewards",
    author = "Akarajaradwong, Pawitsapak  and
      Chaksangchaichot, Chompakorn  and
      Pothavorn, Pirat  and
      Chuangsuwanich, Ekapol  and
      Rutherford, Attapol  and
      Nutanong, Sarana",
    editor = "Aletras, Nikolaos  and
      Chalkidis, Ilias  and
      Barrett, Leslie  and
      Goanț{\u{a}}, C{\u{a}}t{\u{a}}lina  and
      Preoțiuc-Pietro, Daniel  and
      Spanakis, Gerasimos",
    booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.nllp-1.21/",
    pages = "304--316",
    ISBN = "979-8-89176-338-8",
    abstract = "The Retrieval-Augmented Generation (RAG) systems' performance on Thai legal question answering is still limited, especially for questions requiring extensive, complex legal reasoning. To address these limitations, we introduce a resource-efficient approach that aligns Large Language Models (LLMs) for improved citation accuracy and response quality using Group-Relative Policy Optimization (GRPO). Our proposed method leverages BGE-M3 embeddings as a cost-efficient semantic-similarity reward, significantly reducing computational expenses up to 2.5x compared to an LLM-based reward model. Experiments on the NitiBench benchmark demonstrate substantial improvements: GRPO achieves up to 90{\%} citation-F1 gains relative to the base model and a 31{\%} increase in joint quality metrics over instruction tuning. Crucially, our approach provides a practical and effective solution for enhancing legal LLMs in resource-constrained environments."
}