Measuring Retrieval Complexity in Question Answering Systems

Matteo Gabburo, Nicolaas Jedema, Siddhant Garg, Leonardo Ribeiro, Alessandro Moschitti


Abstract
In this paper, we investigate which questions are challenging for retrieval-based Question Answering (QA). We (i) propose retrieval complexity (RC), a novel metric conditioned on the completeness of retrieved documents, which measures the difficulty of answering questions, and (ii) propose an unsupervised pipeline to measure RC given an arbitrary retrieval system.Our proposed pipeline measures RC more accurately than alternative estimators, including LLMs, on six challenging QA benchmarks. Further investigation reveals that RC scores strongly correlate with both QA performance and expert judgment across five of the six studied benchmarks, indicating that RC is an effective measure of question difficulty.Subsequent categorization of high-RC questions shows that they span a broad set of question shapes, including multi-hop, compositional, and temporal QA, indicating that RC scores can categorize a new subset of complex questions. Our system can also have a major impact on retrieval-based systems by helping to identify more challenging questions on existing datasets.
Anthology ID:
2024.findings-acl.872
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14636–14650
Language:
URL:
https://aclanthology.org/2024.findings-acl.872
DOI:
10.18653/v1/2024.findings-acl.872
Bibkey:
Cite (ACL):
Matteo Gabburo, Nicolaas Jedema, Siddhant Garg, Leonardo Ribeiro, and Alessandro Moschitti. 2024. Measuring Retrieval Complexity in Question Answering Systems. In Findings of the Association for Computational Linguistics: ACL 2024, pages 14636–14650, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Measuring Retrieval Complexity in Question Answering Systems (Gabburo et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.872.pdf