Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models

Wenxuan Ding, Shangbin Feng, Yuhan Liu, Zhaoxuan Tan, Vidhisha Balachandran, Tianxing He, Yulia Tsvetkov


Abstract
We propose Knowledge Crosswords, a geometric knowledge reasoning benchmark consisting of incomplete knowledge networks bounded by structured factual constraints, where LLMs are tasked with inferring the missing facts to meet all constraints. The novel setting of geometric knowledge reasoning necessitates new LM abilities beyond existing atomic/linear multi-hop QA, such as backtracking, verifying facts and constraints, reasoning with uncertainty, and more. Knowledge Crosswords contains 2,101 individual problems, covering diverse knowledge domains, and is further divided into three difficulty levels. We conduct extensive experiments to evaluate existing LLMs and approaches on Knowledge Crosswords. Results demonstrate that baseline approaches struggle with larger knowledge networks and semantically-equivalent entity distractors. In light of their limitations, we propose two new approaches, Staged Prompting and Verify-All, to augment LLMs’ abilities for error-aware backtracking and constraint verification. Our Verify-All significantly outperforms prior methods and is more robust towards problems in the hard subset. Further analysis shows that geometric knowledge reasoning poses new challenges to LLMs’ knowledge abilities, particularly in robustness towards varying option orders, complex structural constraints in knowledge networks, “none of the above” scenarios, and more.
Anthology ID:
2024.findings-acl.154
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2609–2636
Language:
URL:
https://aclanthology.org/2024.findings-acl.154
DOI:
10.18653/v1/2024.findings-acl.154
Bibkey:
Cite (ACL):
Wenxuan Ding, Shangbin Feng, Yuhan Liu, Zhaoxuan Tan, Vidhisha Balachandran, Tianxing He, and Yulia Tsvetkov. 2024. Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models. In Findings of the Association for Computational Linguistics ACL 2024, pages 2609–2636, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models (Ding et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.154.pdf