Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
Abstract
In this work, we present a model for documentgrounded 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 opendomain 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 (Rashkin et al., 2021), and show that both approaches can be combined to achieve additional improvements.
Authors 4
-
Technische Universität Darmstadt
Affiliation as printed
Ubiquitous Knowledge Processing Lab Department of Computer Science , Technical University of Darmstadt
Ubiquitous Knowledge Processing Lab Department of Computer Science, Technical University of Darmstadt
-
Affiliation as printed
AppTek GmbH
Chair for Human Language Technology and Pattern Recognition , RWTH Aachen University
AppTek GmbH www
Chair for Human Language Technology and Pattern Recognition, RWTH Aachen University
-
Affiliation as printed
AppTek GmbH
AppTek GmbH www
-
Affiliation as printed
AppTek GmbH
Chair for Human Language Technology and Pattern Recognition , RWTH Aachen University
AppTek GmbH www
Chair for Human Language Technology and Pattern Recognition, RWTH Aachen University
Cited by 1 stored of 1
1 result
No patents citing this paper on Lens.org (checked 2026-10-06).