Learning Style, Forgetting Semantics: A Case Study of SFT and RFT on Classification Tasks

stat.ML, cs.AI, cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: 43 pages, 7 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• A Quantitative Characterization of Forgetting in Post-Training
• Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
• Overcoming catastrophic forgetting in neural networks
• Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
• An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
• Training language models to follow instructions with human feedback
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Self-Distillation Enables Continual Learning

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier