Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence
Published in The 2022 Conference on Empirical Methods in Natural Language Processing, 2022
This paper addresses the challenge of knowledge conflicts that arise when models have access to rich, diverse knowledge sources. We propose methods for recalibrating models to appropriately handle conflicting evidence and reflect uncertainty in their predictions.
Recommended citation: Hung-Ting Chen, Michael J.Q. Zhang, Eunsol Choi. (2022). "Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence." The 2022 Conference on Empirical Methods in Natural Language Processing.
Download Paper