LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
Improved supervised fine-tuning for large language models to mitigate catastrophic forgetting
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
RLVR drives a concept network in LLMs through nucleation and freezing into inverse trees that support slow thinking, and intervening with brief SFT at peak frustration outperforms standard RLVR while post-freeze SFT causes forgetting.
citing papers explorer
-
Crafting Reversible SFT Behaviors in Large Language Models
LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
-
Emergent Slow Thinking in LLMs as Inverse Tree Freezing
RLVR drives a concept network in LLMs through nucleation and freezing into inverse trees that support slow thinking, and intervening with brief SFT at peak frustration outperforms standard RLVR while post-freeze SFT causes forgetting.