The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations

Yubo Zhu, Dongrui Liu, Zecheng Lin, Wei Tong, Sheng Zhong, Jing Shao


Abstract
Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference. Existing methods typically rely on repeated response sampling, auxiliary models, or fine-tuning the target model itself, which may incur substantial computational costs or compromise generality. In this paper, we propose a novel approach for difficulty estimation that leverages only the hidden representations produced by the target LLM. We model the token-level generation process as a Markov chain and define a value function to estimate the expected output quality given any hidden state. This allows for efficient and accurate difficulty estimation based solely on the initial hidden state, without generating any output tokens. Extensive experiments across both textual and multimodal tasks demonstrate that our method consistently outperforms existing baselines in difficulty estimation. Moreover, we apply our difficulty estimates to guide adaptive reasoning strategies, including Self-Consistency, Best-of-N, and Self-Refine, achieving higher inference efficiency with fewer generated tokens.
Anthology ID:
2025.emnlp-main.61
Volume:
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1160–1176
Language:
URL:
https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.61/
DOI:
Bibkey:
Cite (ACL):
Yubo Zhu, Dongrui Liu, Zecheng Lin, Wei Tong, Sheng Zhong, and Jing Shao. 2025. The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 1160–1176, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations (Zhu et al., EMNLP 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.61.pdf
Checklist:
 2025.emnlp-main.61.checklist.pdf