{"id":"2312.16132","title":"RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Models","url":"https://codeofpaper.com/paper/2312.16132","arxiv_url":"https://arxiv.org/abs/2312.16132","published":"2023-12-26","code":"community","best":{"full_name":"Magnetic2014/RoleEval","url":"https://github.com/Magnetic2014/RoleEval","tier":"high_confidence_community","stars":43,"license":null,"framework":null,"language":null,"last_commit":"2024-01-09T06:57:59"},"most_starred_community":null,"implementations":[{"full_name":"Magnetic2014/RoleEval","url":"https://github.com/Magnetic2014/RoleEval","tier":"high_confidence_community","stars":43,"license":null,"framework":null,"language":null,"last_commit":"2024-01-09T06:57:59"}],"possible_matches":1}