ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations

ACL ARR 2025 May Submission5495 Authors

Abstract:

This paper introduces ThoughtProbe, a novel inference-time framework that leverages the hidden reasoning features of Large Language Models (LLMs) to improve their reasoning performance.
Unlike previous works that manipulate the hidden representations to steer LLM generation, we harness them as discriminative signals to guide the tree-structured response space exploration.
In each node expansion, a classifier serves as a scoring and ranking mechanism that efficiently allocates computational resources
by prioritizing higher score candidates for continuation.
After completing the tree expansion, we collect answers from all branches to form a candidate answer pool.
We then propose a branch-aggregation method that marginalizes over all supporting branches by aggregating their CoT scores, thereby identifying the optimal answer from the pool.
Experimental results show that our framework's comprehensive exploration not only covers valid reasoning chains but also effectively identifies them, achieving significant improvements across multiple arithmetic reasoning benchmarks.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: large language models, representations, chain of thought

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 5495