Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs

Sungjae Lee, Hoyoung Kim, Jeongyeon Hwang, Eunhyeok Park, Jungseul Ok


Abstract
Scaling test-time computation, generating and analyzing multiple or sequential outputs for a single input, has become a promising strategy for improving the reliability and quality of large language models (LLMs), as evidenced by advances in uncertainty quantification and multi-step reasoning. A key shared component is semantic clustering, which groups outputs that differ in form but convey the same meaning. Semantic clustering enables estimation of the distribution over the semantics of outputs and helps avoid redundant exploration of reasoning paths. However, existing approaches typically rely on external models, which introduce substantial computational overhead and often fail to capture context-aware semantics. We propose Latent Semantic Clustering (LSC), a lightweight and context-sensitive method that leverages the generator LLM’s internal hidden states for clustering, eliminating the need for external models. Our extensive experiment across various LLMs and datasets shows that LSC significantly improves the computational efficiency of test-time scaling while maintaining or exceeding the performance of existing methods.
Anthology ID:
2025.findings-emnlp.1310
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
24126–24144
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1310/
DOI:
Bibkey:
Cite (ACL):
Sungjae Lee, Hoyoung Kim, Jeongyeon Hwang, Eunhyeok Park, and Jungseul Ok. 2025. Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 24126–24144, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs (Lee et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1310.pdf
Checklist:
 2025.findings-emnlp.1310.checklist.pdf