A training method using reinforcement learning and answerability heuristics lets small language models actively ask for missing math details and then solve problems, raising accuracy on the new GSM-MC benchmark from 0.15% to 73.98%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration
A training method using reinforcement learning and answerability heuristics lets small language models actively ask for missing math details and then solve problems, raising accuracy on the new GSM-MC benchmark from 0.15% to 73.98%.