CREPE: Open-Domain Question Answering with False Presuppositions

TL;DR

CREPE introduces a new open-domain QA dataset with real-world questions containing false presuppositions, highlighting challenges in factual verification and evidence retrieval for improved question answering systems.

Contribution

The paper presents CREPE, a novel dataset capturing presupposition failures in natural questions, and analyzes baseline model performance on this realistic, challenging QA task.

Findings

25% of questions contain false presuppositions

Existing models struggle to verify presupposition correctness

Evidence retrieval remains a key challenge

Abstract

Information seeking users often pose questions with false presuppositions, especially when asking about unfamiliar topics. Most existing question answering (QA) datasets, in contrast, assume all questions have well defined answers. We introduce CREPE, a QA dataset containing a natural distribution of presupposition failures from online information-seeking forums. We find that 25% of questions contain false presuppositions, and provide annotations for these presuppositions and their corrections. Through extensive baseline experiments, we show that adaptations of existing open-domain QA models can find presuppositions moderately well, but struggle when predicting whether a presupposition is factually correct. This is in large part due to difficulty in retrieving relevant evidence passages from a large text corpus. CREPE provides a benchmark to study question answering in the wild, and our analyses provide avenues for future work in better modeling and further studying the task.