IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions

TL;DR

This paper introduces IfQA, a large-scale dataset for evaluating open-domain question answering involving counterfactual presuppositions, highlighting the challenges models face in reasoning about imagined, non-factual scenarios.

Contribution

The creation of the first large-scale counterfactual open-domain QA dataset, IfQA, with over 3,800 questions designed to test reasoning beyond factual knowledge.

Findings

Existing QA models perform poorly on IfQA (EM scores below 40%)

Counterfactual questions significantly challenge current retrieval and reasoning methods

The dataset reveals gaps in models' ability to handle imagined scenarios

Abstract

Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability. To address this void, we introduce the first such dataset, named IfQA, where each question is based on a counterfactual presupposition via an "if" clause. For example, if Los Angeles was on the east coast of the U.S., what would be the time difference between Los Angeles and Paris? Such questions require models to go beyond retrieving direct factual knowledge from the Web: they must identify the right information to retrieve and reason about an imagined situation that may even go against the facts built into their parameters. The IfQA dataset contains over 3,800 questions that were annotated annotated by crowdworkers on relevant Wikipedia passages. Empirical analysis reveals that the IfQA dataset is highly challenging for existing open-domain QA methods, including supervised retrieve-then-read pipeline methods (EM score 36.2), as well as recent few-shot approaches such as chain-of-thought prompting with GPT-3 (EM score 27.4). The unique challenges posed by the IfQA benchmark will push open-domain QA research on both retrieval and counterfactual reasoning fronts.