Lightweight Latent Verifiers for Efficient Meta-Generation Strategies

ICLR 2026 Conference Submission19926 Authors

Keywords: reasoning, large language models, verification, uncertainty estimation, interpretability

TL;DR: We show that it is possible to cheaply and reliably extract correctness signal from the hidden states of LLMs; this is useful in practice to enhance accuracy and compute-efficiency on reasoning tasks.

Abstract: Verifiers are auxiliary models that assess the correctness of outputs generated by base large language models (LLMs). They play a crucial role in many strategies for solving reasoning-intensive problems with LLMs. Typically, verifiers are LLMs themselves, often as large (or larger) than the base model they support, making them computationally expensive. In this work, we introduce a novel lightweight verification approach, LiLaVe, which reliably extracts correctness signals from the hidden states of the base LLM. A key advantage of LiLaVe is its ability to operate with only a small fraction of the computational budget required by traditional LLM-based verifiers. To demonstrate its practicality, we couple LiLaVe with popular meta-generation strategies, like best-of-n or self-consistency. Moreover, we design novel LiLaVe-based approaches, like conditional self-correction or conditional majority voting, that significantly improve both accuracy and efficiency in generation tasks with smaller LLMs. Our work demonstrates the fruitfulness of extracting latent information from the hidden states of LLMs, and opens the door to scalable and resource-efficient solutions for reasoning-intensive applications.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 19926