Few-shot Subgoal Planning with Language Models

Lajanugen Logeswaran, Yao Fu, Moontae Lee, Honglak Lee


Abstract
Pre-trained language models have shown successful progress in many text understanding benchmarks. This work explores the capability of these models to predict actionable plans in real-world environments. Given a text instruction, we show that language priors encoded in pre-trained models allow us to infer fine-grained subgoal sequences. In contrast to recent methods which make strong assumptions about subgoal supervision, our experiments show that language models can infer detailed subgoal sequences from few training sequences without any fine-tuning. We further propose a simple strategy to re-rank language model predictions based on interaction and feedback from the environment. Combined with pre-trained navigation and visual reasoning components, our approach demonstrates competitive performance on subgoal prediction and task completion in the ALFRED benchmark compared to prior methods that assume more subgoal supervision.
Anthology ID:
2022.naacl-main.402
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5493–5506
Language:
URL:
https://aclanthology.org/2022.naacl-main.402
DOI:
10.18653/v1/2022.naacl-main.402
Bibkey:
Cite (ACL):
Lajanugen Logeswaran, Yao Fu, Moontae Lee, and Honglak Lee. 2022. Few-shot Subgoal Planning with Language Models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5493–5506, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Few-shot Subgoal Planning with Language Models (Logeswaran et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.402.pdf
Data
AI2-THORALFRED