Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery
Fine-tuning on datasets of unknown origin can create a backdoor in the trained model when the data includes poisoned examples. Difficult to localise and remove, backdoors can persist through safety training. While parameter-efficient fine-tuning methods capture the full parameter changes introduced during training, they are not easily interpretable. We present the full method of TopKLoRA,…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
