IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions
This addresses a fundamental gap in evaluating AI models' counterfactual reasoning abilities for open-domain QA, though it is incremental as it focuses on dataset creation rather than method development.
The authors tackled the lack of large-scale benchmarks for counterfactual reasoning in open-domain question answering by introducing IfQA, a dataset of over 3,800 questions based on counterfactual presuppositions, which proved highly challenging for existing methods with EM scores as low as 27.4 for GPT-3.
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.