PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset
Uzunoglu A, Safa A, Sahin GG (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: Association for Computational Linguistics (ACL)
Pages Range: 10085-10102
Conference Proceedings Title: Proceedings of the Annual Meeting of the Association for Computational Linguistics
Event location: Hybrid, Bangkok, THA
ISBN: 9798891760998
DOI: 10.18653/v1/2024.findings-acl.599
Abstract
Recently, there has been growing interest within the community regarding whether large language models are capable of planning or executing plans. However, most prior studies use LLMs to generate high-level plans for simplified scenarios lacking linguistic complexity and domain diversity, limiting analysis of their planning abilities. These setups constrain evaluation methods (e.g., predefined action space), architectural choices (e.g., only generative models), and overlook the linguistic nuances essential for realistic analysis. To tackle this, we present PARADISE, an abductive reasoning task using Q&A format on practical procedural text sourced from wikiHow. It involves warning and tip inference tasks directly associated with goals, excluding intermediary steps, with the aim of testing the ability of the models to infer implicit knowledge of the plan solely from the given goal. Our experiments, utilizing fine-tuned language models and zero-shot prompting, reveal the effectiveness of task-specific small models over large language models in most scenarios. Despite advancements, all models fall short of human performance. Notably, our analysis uncovers intriguing insights, such as variations in model behavior with dropped keywords, struggles of BERT-family and GPT-4 with physical and abstract goals, and the proposed tasks offering valuable prior knowledge for other unseen procedural tasks. The PARADISE dataset and associated resources are publicly available for further research exploration with https://github.com/GGLAB-KU/paradise.
Involved external institutions
United States (USA) (US)
Turkey (TR)How to cite
APA:
Uzunoglu, A., Safa, A., & Sahin, G.G. (2024). PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset. In Lun-Wei Ku, Andre Martins, Vivek Srikumar (Eds.), Proceedings of the Annual Meeting of the Association for Computational Linguistics (pp. 10085-10102). Hybrid, Bangkok, THA: Association for Computational Linguistics (ACL).
MLA:
Uzunoglu, Arda, Abdulfattah Safa, and Gözde Gül Sahin. "PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset." Proceedings of the Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024, Hybrid, Bangkok, THA Ed. Lun-Wei Ku, Andre Martins, Vivek Srikumar, Association for Computational Linguistics (ACL), 2024. 10085-10102.
BibTeX: Download