LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.
Injecting new knowledge into large language models via supervised fine-tuning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
Correcting DeepSpeed optimizer and OpenRLHF loss bugs reveals SFT-then-RL outperforms mixed-policy methods by 3.8-22.2 points on math benchmarks.
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.
-
SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
Correcting DeepSpeed optimizer and OpenRLHF loss bugs reveals SFT-then-RL outperforms mixed-policy methods by 3.8-22.2 points on math benchmarks.