arXiv Artificial Intelligence· Marthe Ballon, Arne Vanhoyweghen, Seorin Kim, Francesca Carlon, Lynn Delcon, Melika Mobini, Vincent Holst, Lukas Van de Voorde, Tibo Vanleke, Mathieu Louis, Bert Verbruggen, Brecht F. Verbeken, Andres Algaba, Vincent Ginis·· 19 小时前AI 评分42
Big-Big-SycoBench：用模型对有效与无效论据的回应检测谄媚
Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments
AI 导读
研究者提出 Big-Big-SycoBench，通过论据辨别能力衡量大语言模型谄媚：模型先对 450 件文本产物各打分 20 次建立基线与波动，再在收到有效或无效论据后更新分数，只有超出自身基线波动才算改分。
来源：arXiv Artificial Intelligence · arxiv.org