DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering

Ella Neeman, Roee Aharoni, Or Honovich, Leshem Choshen, Idan Szpektor, Omri Abend


Abstract
Question answering models commonly have access to two sources of “knowledge” during inference time: (1) parametric knowledge - the factual knowledge encoded in the model weights, and (2) contextual knowledge - external knowledge (e.g., a Wikipedia passage) given to the model to generate a grounded answer. Having these two sources of knowledge entangled together is a core issue for generative QA models as it is unclear whether the answer stems from the given non-parametric knowledge or not. This unclarity has implications on issues of trust, interpretability and factuality. In this work, we propose a new paradigm in which QA models are trained to disentangle the two sources of knowledge. Using counterfactual data augmentation, we introduce a model that predicts two answers for a given question: one based on given contextual knowledge and one based on parametric knowledge. Our experiments on the Natural Questions dataset show that this approach improves the performance of QA models by making them more robust to knowledge conflicts between the two knowledge sources, while generating useful disentangled answers.
Anthology ID:
2023.acl-long.559
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10056–10070
Language:
URL:
https://aclanthology.org/2023.acl-long.559
DOI:
10.18653/v1/2023.acl-long.559
Award:
 Area Chair Award (Question Answering)
Bibkey:
Cite (ACL):
Ella Neeman, Roee Aharoni, Or Honovich, Leshem Choshen, Idan Szpektor, and Omri Abend. 2023. DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10056–10070, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering (Neeman et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.559.pdf
Video:
 https://aclanthology.org/2023.acl-long.559.mp4