Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA

TL;DR

This paper introduces CAIMIRA, a framework based on item response theory, to quantitatively compare human and AI question-answering abilities, revealing distinct strengths and weaknesses in knowledge and reasoning domains.

Contribution

The paper presents CAIMIRA, a novel IRT-based framework for assessing and comparing human and AI problem-solving skills in QA tasks, with extensive empirical analysis.

Findings

Humans excel in abductive and conceptual reasoning.

AI systems outperform in information retrieval and fact-based reasoning.

Different proficiency patterns highlight complementary strengths between humans and AI.

Abstract

Recent advancements of large language models (LLMs) have led to claims of AI surpassing humans in natural language processing (NLP) tasks such as textual understanding and reasoning. This work investigates these assertions by introducing CAIMIRA, a novel framework rooted in item response theory (IRT) that enables quantitative assessment and comparison of problem-solving abilities of question-answering (QA) agents: humans and AI systems. Through analysis of over 300,000 responses from ~70 AI systems and 155 humans across thousands of quiz questions, CAIMIRA uncovers distinct proficiency patterns in knowledge domains and reasoning skills. Humans outperform AI systems in knowledge-grounded abductive and conceptual reasoning, while state-of-the-art LLMs like GPT-4 and LLaMA show superior performance on targeted information retrieval and fact-based reasoning, particularly when information gaps are well-defined and addressable through pattern matching or data retrieval. These findings highlight the need for future QA tasks to focus on questions that challenge not only higher-order reasoning and scientific thinking, but also demand nuanced linguistic interpretation and cross-contextual knowledge application, helping advance AI developments that better emulate or complement human cognitive abilities in real-world problem-solving.