LLMs on interactive feature collections with implicit dynamic decision strategy

Juyeon Heo, Vihari Piratla, Kyunghyun Lee, Hyonkeun Joh, Adrian Weller


Abstract
In real-world contexts such as medical diagnosis and business consulting, effective problem-solving often requires gathering relevant information through interactions and targeted questioning to pinpoint the root cause of a problem. However, Large Language Models (LLMs) often struggle to efficiently narrow down the search space, leading to either missing key information or asking redundant questions when guided by implicit methods like Chain-of-Thought (CoT). Some approaches employ external engineered systems to guide reasoning paths, but these methods may not fully utilize the inherent problem-solving capabilities of LLMs and often require multiple expensive API calls. This study explores how we can implicitly guide LLMs to enhance their interactive feature collection abilities within a single prompt. Instead of employing explicit search algorithms or step-by-step external guidance, we provide high-level guidelines that allow LLMs to dynamically adjust their strategies and iteratively refine their decision-making processes independently. Evaluations on synthetic 20-Questions games and real-world scenarios, including business and medical diagnosis cases, demonstrate that LLMs guided by these strategies perform more effective interactive feature collection, asking fewer and more strategic questions and achieving better problem-solving efficiency.
Anthology ID:
2025.coling-main.53
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
786–811
Language:
URL:
https://aclanthology.org/2025.coling-main.53/
DOI:
Bibkey:
Cite (ACL):
Juyeon Heo, Vihari Piratla, Kyunghyun Lee, Hyonkeun Joh, and Adrian Weller. 2025. LLMs on interactive feature collections with implicit dynamic decision strategy. In Proceedings of the 31st International Conference on Computational Linguistics, pages 786–811, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
LLMs on interactive feature collections with implicit dynamic decision strategy (Heo et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.53.pdf