Cheater's Bowl: Human vs. Computer Search Strategies for Open-Domain Question Answering

TL;DR

This paper compares human and computer search strategies for open-domain question answering, using a gamified interface to collect data and analyze differences, with implications for improving QA system design.

Contribution

It introduces Cheater's Bowl, a novel gamified data collection method, and provides insights into human search strategies for enhancing QA models.

Findings

Humans query logically and use dynamic search chains.

Human strategies can improve QA system accuracy.

Humans leverage world knowledge to boost searches.

Abstract

For humans and computers, the first step in answering an open-domain question is retrieving a set of relevant documents from a large corpus. However, the strategies that computers use fundamentally differ from those of humans. To better understand these differences, we design a gamified interface for data collection -- Cheater's Bowl -- where a human answers complex questions with access to both traditional and modern search tools. We collect a dataset of human search sessions, analyze human search strategies, and compare them to state-of-the-art multi-hop QA models. Humans query logically, apply dynamic search chains, and use world knowledge to boost searching. We demonstrate how human queries can improve the accuracy of existing systems and propose improving the future design of QA models.