{"id":"aligning-with-human-judgement-the-role-of-pairwise-preferenc","name":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","desc":"研究成对偏好在LLM评估中对齐人类判断的论文","url":"https://arxiv.org/html/2403.16950v2","category":"对话助手","tags":["LLM"],"rating":0,"users":null,"updated":"2026-04-08T00:00:00.000Z","source":"filipecalegario/awesome-generative-ai","addedAt":"2026-04-08T00:00:00.000Z","hot":false,"isNew":false}