@inproceedings{dalvi-mishra-etal-2022-towards,
    title = "Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement",
    author = "Dalvi Mishra, Bhavana  and
      Tafjord, Oyvind  and
      Clark, Peter",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.emnlp-main.644/",
    doi = "10.18653/v1/2022.emnlp-main.644",
    pages = "9465--9480",
    abstract = "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 toerroneous 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 situations - a novel application of memory-based continuous learning. With simulated feedback, we find that our system (called TeachMe) continually improves with time, and without model retraining, requiring feedback on only 25{\%} of training examples to reach within 1{\%} of the upper-bound (feedback on all examples). Similarly, in experiments with real users, we observe a similar trend, with performance improving by over 15{\%} on a hidden test set after teaching. This suggests new opportunities for using frozen language models in an interactive setting where users can inspect, debug, and correct the model{'}s beliefs, leading to improved system{'}s performance over time."
}