RelativePreferenceOptimization

書いてみる

関連タグ

#Adaptability (8)
#ContrastingResponses (1)
#LLMAlignment (1)
#データ (34,628)
#使用 (4,129)
#手法 (5,151)

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts

Ikemen Mas Kot
9か月前