Mathematical Transfer in LLMs Follows Reasoning Approach More Than Topic
Quick summary
arXiv:2610.00331v1 Announce Type: new Abstract: When selecting mathematical training data for LLMs, a natural organizing principle is topic: probability examples for probability targets. An alternative is reasoning approach: worked solutions that share a solution method with the target, even when the mathematical domain differs. We ask which relation produces greater transfer after fine-tuning. We evaluate two counterbalanced $2\times2$ designs: probability and combinatorics crossed with invariant reasoning and double counting (2,000 problems), and number theory and geometry crossed with compl
Key takeaways
- arXiv:2610.00331v1 Announce Type: new Abstract: When selecting mathematical training data for LLMs, a natural organizing principle is topic: probability examples for probability targets.
- An alternative is reasoning approach: worked solutions that share a solution method with the target, even when the mathematical domain differs.
- We ask which relation produces greater transfer after fine-tuning.
Why it matters
“Mathematical Transfer in LLMs Follows Reasoning Approach More Than Topic” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments