Fine-tuning Llama-3.1-8B to generate Prolog programs from a fixed 54-operator library reportedly reaches 84.8% on MATH counting/probability, but test-set solutions were added to training, so the headline is not a clean held-out result.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Enhancing Mathematical Reasoning in LLMs with Background Operators
Fine-tuning Llama-3.1-8B to generate Prolog programs from a fixed 54-operator library reportedly reaches 84.8% on MATH counting/probability, but test-set solutions were added to training, so the headline is not a clean held-out result.