Multi-Hop Question Answering: When Can Humans Help, and Where do They Struggle?

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Su, Jinyan, Cardie, Claire, Healey, Jennifer
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908577396948992
author Su, Jinyan
Cardie, Claire
Healey, Jennifer
author_facet Su, Jinyan
Cardie, Claire
Healey, Jennifer
contents Multi-hop question answering is a challenging task for both large language models (LLMs) and humans, as it requires recognizing when multi-hop reasoning is needed, followed by reading comprehension, logical reasoning, and knowledge integration. To better understand how humans might collaborate effectively with AI, we evaluate the performance of crowd workers on these individual reasoning subtasks. We find that while humans excel at knowledge integration (97\% accuracy), they often fail to recognize when a question requires multi-hop reasoning (67\% accuracy). Participants perform reasonably well on both single-hop and multi-hop QA (84\% and 80\% accuracy, respectively), but frequently make semantic mistakes--for example, answering "when" an event happened when the question asked "where." These findings highlight the importance of designing AI systems that complement human strengths while compensating for common weaknesses.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04493
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Hop Question Answering: When Can Humans Help, and Where do They Struggle?
Su, Jinyan
Cardie, Claire
Healey, Jennifer
Human-Computer Interaction
Multi-hop question answering is a challenging task for both large language models (LLMs) and humans, as it requires recognizing when multi-hop reasoning is needed, followed by reading comprehension, logical reasoning, and knowledge integration. To better understand how humans might collaborate effectively with AI, we evaluate the performance of crowd workers on these individual reasoning subtasks. We find that while humans excel at knowledge integration (97\% accuracy), they often fail to recognize when a question requires multi-hop reasoning (67\% accuracy). Participants perform reasonably well on both single-hop and multi-hop QA (84\% and 80\% accuracy, respectively), but frequently make semantic mistakes--for example, answering "when" an event happened when the question asked "where." These findings highlight the importance of designing AI systems that complement human strengths while compensating for common weaknesses.
title Multi-Hop Question Answering: When Can Humans Help, and Where do They Struggle?
topic Human-Computer Interaction
url https://arxiv.org/abs/2510.04493