Large language models (LLMs) are being increasingly integrated into legal applications, including judicial decision support, legal practice assistance, and public-facing legal services. While LLMs show strong potential in handling legal knowledge and tasks, their deployment in real-world legal settings raises critical concerns beyond surface-level accuracy, involving the soundness of legal reasoning processes and trustworthy issues such as fairness and reliability. Systematic evaluation of LLM performance in legal tasks has therefore become essential for their responsible adoption. This survey identifies key challenges in evaluating LLMs for legal tasks grounded in real-world legal practice. We analyze the major difficulties involved in assessing LLM performance in the legal domain, including outcome correctness, reasoning reliability, and trustworthiness. Building on these challenges, we review and categorize existing evaluation methods and benchmarks according to their task design, datasets, and evaluation metrics. We further discuss the extent to which current approaches address these challenges, highlight their limitations, and outline future research directions toward more realistic, reliable, and legally grounded evaluation frameworks for LLMs in legal domains.
@article{arxiv.2601.15267,
title = {Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions},
author = {Yiran Hu and Huanghai Liu and Chong Wang and Kunran Li and Tien-Hsuan Wu and Haitao Li and Xinran Xu and Siqing Huo and Weihang Su and Ning Zheng and Siyuan Zheng and Qingyao Ai and Yun Liu and Renjun Bian and Yiqun Liu and Charles L. A. Clarke and Weixing Shen and Ben Kao},
journal= {arXiv preprint arXiv:2601.15267},
year = {2026}
}