Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback

Nikhil Mehta, Milagro Teruel, Xin Deng, Sergio Figueroa Sanz, Ahmed Awadallah, Julia Kiseleva


Abstract
Many approaches to Natural Language Processing tasks often treat them as single-step problems, where an agent receives an instruction, executes it, and is evaluated based on the final outcome. However, language is inherently interactive, as evidenced by the back-and-forth nature of human conversations. In light of this, we posit that human-AI collaboration should also be interactive, with humans monitoring the work of AI agents and providing feedback that the agent can understand and utilize. Further, the AI agent should be able to detect when it needs additional information and proactively ask for help. Enabling this scenario would lead to more natural, efficient, and engaging human-AI collaboration.In this paper, we investigate these directions using the challenging task established by the IGLU competition, an interactive grounded language understanding task in a MineCraft-like world. We delve into multiple types of help players can give to the AI to guide it and analyze the impact of this help on behavior, resulting in performance improvements and an end-to-end interactive system.
Anthology ID:
2024.findings-eacl.87
Volume:
Findings of the Association for Computational Linguistics: EACL 2024
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1306–1321
Language:
URL:
https://aclanthology.org/2024.findings-eacl.87
DOI:
Bibkey:
Cite (ACL):
Nikhil Mehta, Milagro Teruel, Xin Deng, Sergio Figueroa Sanz, Ahmed Awadallah, and Julia Kiseleva. 2024. Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1306–1321, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback (Mehta et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-eacl.87.pdf
Video:
 https://aclanthology.org/2024.findings-eacl.87.mp4