Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models

Sungjae Lee, Hyejin Park, Jaechang Kim, Jungseul Ok


Abstract
Recent advancements in large language models (LLMs) have shown remarkable potential in various complex tasks requiring multi-step reasoning methods like tree search to explore diverse reasoning paths. However, existing methods often suffer from computational inefficiency and redundancy. First, they overlook the diversity of task difficulties, leading to unnecessarily extensive searches even for easy tasks. Second, they neglect the semantics of reasoning paths, resulting in redundant exploration of semantically identical paths. To address these limitations, we propose Semantic Exploration with Adaptive Gating (SEAG), a computationally efficient method. SEAG employs an adaptive gating mechanism that dynamically decides whether to conduct a tree search, based on the confidence level of answers from a preceding simple reasoning method. Furthermore, its tree-based exploration consolidates semantically identical reasoning steps, reducing redundant explorations while maintaining or even improving accuracy. Our extensive experiments demonstrate that SEAG significantly improves accuracy by 4.3% on average while requiring only 31% of computational costs compared to existing tree search-based methods on complex reasoning benchmarks including GSM8K and ARC with diverse language models such as Llama2, Llama3, and Mistral. Our code is available at https://github.com/ml-postech/SEAG-semantic-exploration-with-adaptive-gating.
Anthology ID:
2025.acl-long.29
Volume:
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2025
Address:
Vienna, Austria
Editors:
Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
588–606
Language:
URL:
https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.29/
DOI:
Bibkey:
Cite (ACL):
Sungjae Lee, Hyejin Park, Jaechang Kim, and Jungseul Ok. 2025. Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 588–606, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models (Lee et al., ACL 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.29.pdf