Fine-tuning Qwen2.5-MATH-7B on LLM-back-translated traces from a SymPy tool agent gives small gains on AIME, AMC, and Olympiad Bench and small losses on MATH500 and GSM8K.
PAL: program-aided language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Distilling Tool Knowledge into Language Models via Back-Translated Traces
Fine-tuning Qwen2.5-MATH-7B on LLM-back-translated traces from a SymPy tool agent gives small gains on AIME, AMC, and Olympiad Bench and small losses on MATH500 and GSM8K.