Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models

Lingjun Zhao, Khanh Nguyen, Hal Daumé III


Abstract
Recent work studies the cognitive capabilities of language models through psychological tests designed for humans. While these studies are helpful for understanding the general capabilities of these models, there is no guarantee that a model possessing sufficient capabilities to pass those tests would actually use those capabilities in performing real-life tasks. In this work, we formulate task-oriented cognitive capabilities, which are human-like cognitive capabilities that language models leverage to perform tasks. These capabilities are (i) the ability to quickly generate good candidate utterances (the search capability) (ii) the ability to predict how a listener interprets those utterances and choose the most appropriate one (the pragmatic capability). We design an evaluation scheme for comparing these capabilities of a language model with those of a human. Applying this scheme to examine various models in a navigation instruction generation problem, we find that their pragmatic capability is severely lacking. This insight leads us to augment them with better models of the listener and obtain a significant boost of 11% in success rate in guiding real humans. Our work advocates for having a principled procedure for aligning language models with humans that involves (i) formulating task-oriented capabilities, (ii) devising a method to quantify their deficiency, and (iii) iteratively improving them.
Anthology ID:
2023.findings-acl.227
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3688–3706
Language:
URL:
https://aclanthology.org/2023.findings-acl.227
DOI:
10.18653/v1/2023.findings-acl.227
Bibkey:
Cite (ACL):
Lingjun Zhao, Khanh Nguyen, and Hal Daumé III. 2023. Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3688–3706, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Models (Zhao et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.227.pdf
Video:
 https://aclanthology.org/2023.findings-acl.227.mp4