Reasoning about Ambiguous Definite Descriptions

Stefan Schouten, Peter Bloem, Ilia Markov, Piek Vossen


Abstract
Natural language reasoning plays an increasingly important role in improving language models’ ability to solve complex language understanding tasks. An interesting use case for reasoning is the resolution of context-dependent ambiguity. But no resources exist to evaluate how well Large Language Models can use explicit reasoning to resolve ambiguity in language. We propose to use ambiguous definite descriptions for this purpose and create and publish the first benchmark dataset consisting of such phrases. Our method includes all information required to resolve the ambiguity in the prompt, which means a model does not require anything but reasoning to do well. We find this to be a challenging task for recent LLMs. Code and data available at: https://github.com/sfschouten/exploiting-ambiguity
Anthology ID:
2023.findings-emnlp.296
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4479–4484
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.296
DOI:
10.18653/v1/2023.findings-emnlp.296
Bibkey:
Cite (ACL):
Stefan Schouten, Peter Bloem, Ilia Markov, and Piek Vossen. 2023. Reasoning about Ambiguous Definite Descriptions. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4479–4484, Singapore. Association for Computational Linguistics.
Cite (Informal):
Reasoning about Ambiguous Definite Descriptions (Schouten et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.296.pdf