张钰.; 宋馨. From Benchmarks to Courtrooms: A Capability–Reliability–Accountability Survey of Large Language Models in Legal Practice. International Journal of Advanced AI Applications, [S. l.], v. 2, n. 9, p. 80–98, 2026. Disponível em: https://www.dawnclarity.press/index.php/ijaaa/article/view/186. Acesso em: 29 sep. 2026.