Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections

Lingjun Zhao, Khanh Nguyen, Hal Daumé Iii


Abstract
Language models will inevitably err in situations with which they are unfamiliar. However, by effectively communicating uncertainties, they can still guide humans toward making sound decisions in those contexts. We demonstrate this idea by developing HEAR, a system that can successfully guide humans in simulated residential environments despite generating potentially inaccurate instructions. Diverging from systems that provide users with only the instructions they generate, HEAR warns users of potential errors in its instructions and suggests corrections. This rich uncertainty information effectively prevents misguidance and reduces the search space for users. Evaluation with 80 users shows that HEAR achieves a 13% increase in success rate and a 29% reduction in final location error distance compared to only presenting instructions to users. Interestingly, we find that offering users possibilities to explore, HEAR motivates them to make more attempts at the task, ultimately leading to a higher success rate. To our best knowledge, this work is the first to show the practical benefits of uncertainty communication in a long-horizon sequential decision-making problem.
Anthology ID:
2024.emnlp-main.42
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:
719–736
Language:
URL:
https://aclanthology.org/2024.emnlp-main.42
DOI:
Bibkey:
Cite (ACL):
Lingjun Zhao, Khanh Nguyen, and Hal Daumé Iii. 2024. Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 719–736, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections (Zhao et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.42.pdf