T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models

Understand

Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs).

• However, prior research has mainly examined test-time compute scaling with an additional larger model as a verifier, leaving verification by sLMs underexplored.
• In this work, we investigate whether sLMs can reliably verify the output candidates under test-time scaling.
• We find that even with knowledge distillation from larger verifiers, sLMs struggle with verification tasks requiring memorization, such as numerical calculations and fact-checking.