General and legal domain LLMs have demonstrated strong performance in various tasks of LegalAI. However, their current evaluations lack alignment with the fundamental logic of legal reasoning, the legal syllogism. This hinders trust and understanding from legal experts. To bridge this gap, we introduce LAiW, the Chinese legal LLM benchmark structured around the legal syllogism. We evaluate legal LLMs across three levels of capability, each reflecting a progressively more complex stage of legal syllogism: fundamental information retrieval, legal principles inference, and advanced legal applications, and encompassing a wide range of tasks in different legal scenarios. Our automatic evaluation reveals that LLMs, despite their ability to answer complex legal questions, lack the inherent logical processes of the legal syllogism. This limitation poses a barrier to acceptance by legal professionals. Furthermore, manual evaluation with legal experts confirms this issue and highlights the importance of pre-training on legal text to enhance the legal syllogism of LLMs. Future research may prioritize addressing this gap to unlock the full potential of LLMs in legal applications.

Existing legal benchmarks focusing on knowledge and logic effectively evaluate LLMs on various tasks in legal domain. However, few have explored the practical application of LLMs by actual users. To further assess whether LLMs meet the specific needs of legal practitioners in real-world scenarios, we introduce UCL-Bench, a Chinese User-Centric Legal Benchmark, comprising 22 tasks across 5 distinct legal scenarios.To build the UCL-Bench, we conduct a user survey targeting legal professionals to understand their needs and challenges. Based on the survey results, we craft tasks, verified by legal professionals, and categorized them according to Bloom’s taxonomy. Each task in UCL-Bench mirrors real-world legal scenarios, and instead of relying on pre-defined answers, legal experts provide detailed answer guidance for each task, incorporating both “information” and “needs” elements to mimic the complexities of legal practice. With the guidance, we use GPT-4 as the user simulator and evaluator, enabling multi-turn dialogues as a answer guidance based evaluation framework. Our findings reveal that many recent open-source general models achieve the highest performance, suggesting that they are well-suited to address the needs of legal practitioners. However, these legal LLMs do not outperform ChatGPT, indicating a need for training strategies aligned with users’ needs. Furthermore, we find that the most effective models are able to address legal issues within fewer dialogue turns, highlighting the importance of concise and accurate responses in achieving high performance. The code and dataset are available at https://github.com/wittenberg11/UCL-bench.

We present our approach to the COLING-2025 Regulations Challenge, which evaluates large language models (LLMs) on nine regulatory tasks, such as abbreviation recognition and financial data extraction. To address challenges like domain-specific terminologies and dynamic regulatory contexts, we developed a robust data construction pipeline, integrating proprietary Chinese regulatory data, Fin-GPT datasets, and financial Q&A data. The pipeline applied, but was not limited to, language filtering, semantic screening, and deduplication, resulting in a 30,000-example dataset combining financial regulations and general financial data. Using this dataset, we fine-tuned Llama 3.2-3B-Instruct to create Reg-LLaMA, a specialized model that outperformed baselines on the Regulations Challenge and PIXIU datasets. These results demonstrate the effectiveness of domain-specific data construction in advancing LLMs for regulatory tasks, paving the way for reliable and interpretable AI in regulated industries.