Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
This work addresses the challenge of ensuring factuality in dialog systems for applications like customer service or information retrieval, though it is incremental as it builds on existing noisy channel models and combines with prior methods.
The authors tackled the problem of generating factual responses in document-grounded dialog systems by decomposing the model into two components based on Bayes theorem, with experiments showing improved factuality over baselines and controllable tradeoffs between factuality and fluency.
In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes theorem. One component is a traditional ungrounded response generation model and the other component models the reconstruction of the grounding document based on the dialog context and generated response. We propose different approximate decoding schemes and evaluate our approach on multiple open-domain and task-oriented document-grounded dialog datasets. Our experiments show that the model is more factual in terms of automatic factuality metrics than the baseline model. Furthermore, we outline how introducing scaling factors between the components allows for controlling the tradeoff between factuality and fluency in the model output. Finally, we compare our approach to a recently proposed method to control factuality in grounded dialog, CTRL (arXiv:2107.06963), and show that both approaches can be combined to achieve additional improvements.