Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for System Improvement

EMNLP'22 talk for paper: https://www.semanticscholar.org/paper/Towards-Teachable-Reasoning-Systems%3A-Using-a-Memory-Dalvi-Tafjord/e7d75b80e0fa3ae190ff91676dbf18a006d3a311

Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. Our approach is to augment a QA model with a dynamic memory of user feedback, containing user-supplied corrections to erroneous model beliefs that users identify during interaction. Retrievals from memory are used as additional context for QA, to help avoid previous mistakes in similar new …

feedback improvement memory reasoning systems user feedback