Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models
This addresses a bottleneck in enhancing LLM capabilities for mathematical tasks, though it is incremental as it builds on existing tree-search strategies.
The paper tackled the suboptimal performance of existing verifiers in tree search for mathematical problem-solving with LLMs by proposing token-supervised value models (TVMs), which improved accuracy significantly over prior methods.
With the rapid advancement of test-time compute search strategies to improve the mathematical problem-solving capabilities of large language models (LLMs), the need for building robust verifiers has become increasingly important. However, all these inference strategies rely on existing verifiers originally designed for Best-of-N search, which makes them sub-optimal for tree search techniques at test time. During tree search, existing verifiers can only offer indirect and implicit assessments of partial solutions or under-value prospective intermediate steps, thus resulting in the premature pruning of promising intermediate steps. To overcome these limitations, we propose token-supervised value models (TVMs) - a new class of verifiers that assign each token a probability that reflects the likelihood of reaching the correct final answer. This new token-level supervision enables TVMs to directly and explicitly evaluate partial solutions, effectively distinguishing between promising and incorrect intermediate steps during tree search at test time. Experimental results demonstrate that combining tree-search-based inference strategies with TVMs significantly improves the accuracy of LLMs in mathematical problem-solving tasks, surpassing the performance of existing verifiers.