# DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering Source: [DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering]() Collection index: [llms.txt]() Data updated: 2026-01-01T15:39:57.067Z Authors: Ella Neeman, Roee Aharoni, Or Honovich, Leshem Choshen, Idan Szpektor, Omri Abend Published: 2022-11-10T15:34:44.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()