# Can Group Relative Policy Optimization Improve Thai Legal Reasoning and Question Answering?

arXiv: https://arxiv.org/abs/2507.09638 · HTML: https://mlsanity.com/paper/2507.09638/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 0 of its 35 references that are in the map.
- First posted on arXiv 13 Jul 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Built on by (most cited first, 1 of 1)

- [LRAS: Advanced Legal Reasoning with Agentic Search](https://mlsanity.com/paper/2601.07296/) (2026)

## Abstract (arXiv)

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 an approach aligning LLMs toward improved law citation accuracy and better response quality using Group-Relative Policy Optimization (GRPO). Our approach leverages BGE-M3 embeddings as a cost-efficient semantic-similarity reward, significantly reducing computational expenses up to 2.5x compared to large language model judges. Experiments on the NitiBench benchmark demonstrate substantial improvements: GRPO achieves up to 90% citation-F1 gains from the base model and a 31% increase in joint quality metrics over instruction tuning. Crucially, our method shows enhanced robustness on complex legal reasoning tasks compared to instruction tuning, providing an effective and resource-efficient solution for enhancing Thai legal LLMs.