Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Stefano Ermon, Chelsea Finn, Christopher D. Manning, Eric Mitchell, Rafael Rafailov, Archit Sharma
Topics & Concepts
PsychologyPreferenceLanguage modelCognitive psychologySocial psychologyComputer scienceArtificial intelligenceStatistical modelNatural language processingControl (management)Constraint Satisfaction and OptimizationDecision-Making and Behavioral EconomicsGame Theory and Voting Systems