Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, Christopher D. Manning
Abstract
Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, Christopher Manning. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
Topics & Concepts
Ask priceCalibrationComputer scienceTianArtificial intelligenceStatisticsArtMathematicsLiteratureEconomyEconomicsTopic ModelingNatural Language Processing Techniques