Open access
2026
Diagnosing Chinese Legal LLMs Across Memorization, Understanding, and Application: The Newtouch-LawBench Benchmark
With the emergence of large language models (LLMs) as strong performers across diverse natural language tasks, high-stakes and knowledge-intensive domains such as law impose stricter requirements on factual reliability, norm-conformant application, and verifiable reasoning. Although existing Chinese legal evaluation be...
Ruo-Chen Lin, Le-Kang Zhang, Hao Wang et al.
· IEEE Access · 0 citations