method
active
method:fine-tuning-sftfine-tuning (SFT)
Supervised fine-tuning to adapt model parameters.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Supervised Fine-tuning (SFT)related_toFull fine-tuning of GPT-4o on synthetic datasets; primary method for inducing emergent misalignment
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Parameter updates that reduce mismatch dr; another anchoring variant in UCCT.
- The patient, hand-guided adjustment of shape and dimension to each unique condition in a building; requires materials that make it economical and easy.
- First post-training stage; shown to suppress only Impolite persona while boosting others
- OpenAI's internal RL fine-tuning API used to train models with graders rewarding correct or incorrect responses
- The literature documenting how fine-tuning can compromise safety alignment even without malicious intent
- Fine-tuning Claude 3 Opus on ~70M tokens of synthetic internet-like documents containing key situational information
- Competing method from Casademunt et al. that zero-ablates concept directions during finetuning; compared against preventative steering
- Training procedure that consistently increases HH-intent strength and consistency across model families.