Post
75
I tinkered a bit with refusal ablation after seeing this article that proposed using optimal transport.
https://arxiv.org/abs/2603.04355
Title: Efficient Refusal Ablation in LLM through Optimal Transport
Authors: Geraldin Nanfack, Eugene Belilovsky, Elvis Dohmatob
While closed Bures-Wasserstein sounded cool, the use of top-K at low K implied that the approach likely wouldn't capture refusal in detail, and increasing KL divergence with greater K suggested that the approach was too damaging for latent reasoning. I tried it out, and the results were disappointing.
https://arxiv.org/abs/2603.04355
Title: Efficient Refusal Ablation in LLM through Optimal Transport
Authors: Geraldin Nanfack, Eugene Belilovsky, Elvis Dohmatob
While closed Bures-Wasserstein sounded cool, the use of top-K at low K implied that the approach likely wouldn't capture refusal in detail, and increasing KL divergence with greater K suggested that the approach was too damaging for latent reasoning. I tried it out, and the results were disappointing.
