# Generative Context Pair Selection for Multi-hop Question Answering Source: [Generative Context Pair Selection for Multi-hop Question Answering]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:09:38.543Z Authors: Dheeru Dua, Cicero Nogueira dos Santos, Patrick Ng, Ben Athiwaratkun, Bing Xiang, Matt Gardner, Sameer Singh Published: 2021-04-18T07:00:48.000Z ## Abstract Compositional reasoning tasks like multi-hop question answering, require making latent decisions to get the final answer, given a question. However, crowdsourced datasets often capture only a slice of the underlying task distribution, which can induce unanticipated biases in models performing compositional reasoning. Furthermore, discriminatively trained models exploit such biases to get a better held-out performance, without learning the right way to reason, as they do not necessitate paying attention to the question representation (conditioning variable) in its entirety, to estimate the answer likelihood. In this work, we propose a generative context selection model for multi-hop question answering that reasons about how the given question could have been generated given a context pair. While being comparable to the state-of-the-art answering performance, our proposed generative passage selection model has a better performance (4.9% higher than baseline) on adversarial held-out set which tests robustness of model's multi-hop reasoning capabilities. ## 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]()