Creative Commons source reading · Search and retrieval
Aligning LLMs for Thai Legal Question Answering with Efficient Semantic-Similarity Rewards
Pawitsapak Akarajaradwong; Chompakorn Chaksangchaichot; Pirat Pothavorn; Ekapol Chuangsuwanich; Attapol Rutherford; Sarana Nutanong
Originally published in Proceedings of the Natural Legal Language Processing Workshop 2025 · 2025-11
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
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.
Editorial reading guide
- Which legal corpus, jurisdiction and evaluation task does the article use?
- What evidence supports the reported performance, and where could the method fail in practice?
