Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering

Armin Toroghi, Willis Guo, Mohammad Mahdi Abdollah Pour, Scott Sanner


Abstract
Knowledge Graph Question Answering (KGQA) methods seek to answer Natural Language questions using the relational information stored in Knowledge Graphs (KGs). With the recent advancements of Large Language Models (LLMs) and their remarkable reasoning abilities, there is a growing trend to leverage them for KGQA. However, existing methodologies have only focused on answering factual questions, e.g., *“In which city was Silvio Berlusconi’s first wife born?”*, leaving questions involving commonsense reasoning that real-world users may pose more often, e.g., *“Do I need separate visas to see the Venus of Willendorf and attend the Olympics this summer?”* unaddressed. In this work, we first observe that existing LLM-based methods for KGQA struggle with hallucination on such questions, especially on queries targeting long-tail entities (e.g., non-mainstream and recent entities), thus hindering their applicability in real-world applications especially since their reasoning processes are not easily verifiable. In response, we propose Right for Right Reasons (R3), a commonsense KGQA methodology that allows for a verifiable reasoning procedure by axiomatically surfacing intrinsic commonsense knowledge of LLMs and grounding every factual reasoning step on KG triples. Through experimental evaluations across three different tasks—question answering, claim verification, and preference matching—our findings showcase R3 as a superior approach, outperforming existing methodologies and notably reducing instances of hallucination and reasoning errors.
Anthology ID:
2024.emnlp-main.378
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6601–6633
Language:
URL:
https://aclanthology.org/2024.emnlp-main.378/
DOI:
10.18653/v1/2024.emnlp-main.378
Bibkey:
Cite (ACL):
Armin Toroghi, Willis Guo, Mohammad Mahdi Abdollah Pour, and Scott Sanner. 2024. Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 6601–6633, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering (Toroghi et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.378.pdf
Software:
 2024.emnlp-main.378.software.zip
Data:
 2024.emnlp-main.378.data.zip