Many thanks for sparking this discussion, Fabien. I see Addie addressed the technical distinctions. Let me add complementary points. Please feel free to continue the conversation in either one. Addie and I can coordinate a response.
In a nutshell, Unlearn-and-Distill allows you to work at the model behavior level rather than the training data level. I mostly view it as a responsive tool, not a preventive one. Here are my thoughts organized into subclaims.
Claim: The fundamental difference between unlearning and data filtering lies in when and how we identify harmful content. Rationale: Data filtering requires identifying "data -> capabilities" patterns in advance, while behavioral unlearning targets actual harmful outputs after they emerge. This matters because harmful capabilities often arise from non-obvious combinations of benign knowledge. Even if creating a classifier is computationally similar to unlearning, you're solving fundamentally different problems: (original framing) predicting emergent behaviors from raw data versus (new framing) suppressing already observed behaviors. With unlearning, you can iteratively refine until you achieve the desired behavior, then distill. With data filtering, you don't know the effects of your filtering until after training completes.
Claim: Computational efficiency is not the only value added from this work. Unlearn + distill requires significantly less labeled data than data filtering. Rationale: Most unlearning procedures only use labels of a small fraction of the pretraining data. In our setup, it was less than 0.01% for language. This eases the data labeling requirement. At modern scales, the difference between labeling 0.01% vs 100% represents substantial annotation efforts. Note that we distilled on the whole pretraining data, but none of it was labeled. The suggestions about value heads or KV cache reuse are interesting optimizations worth exploring, though they don't address this fundamental labeling asymmetry.
Claim: Our robustness metric undersells the method's performance, though stronger attacks may exist. Rationale: The adversary is extremely strong (best of 9 learning rates, 500 training steps, 8M tokens for language, 2M tokens for arithmetic). Even the oracle model (never trained on the forget domain) reaches 50% performance under this attack in arithmetic tasks.
Separately, while 30% compute for 50% robustness (compared to data filtering) isn't cheap, this tradeoff didn't exist before. The value add of UNDO over Unlearn-and-Distill is that it provides a tunable compute/robustness knob between the conventional unlearning and full reinitialization/data filtering
Many thanks for sparking this discussion, Fabien. I see Addie addressed the technical distinctions. Let me add complementary points. Please feel free to continue the conversation in either one. Addie and I can coordinate a response.
In a nutshell, Unlearn-and-Distill allows you to work at the model behavior level rather than the training data level. I mostly view it as a responsive tool, not a preventive one. Here are my thoughts organized into subclaims.
Claim: The fundamental difference between unlearning and data filtering lies in when and how we identify harmful content.
Rationale: Data filtering requires identifying "data -> capabilities" patterns in advance, while behavioral unlearning targets actual harmful outputs after they emerge. This matters because harmful capabilities often arise from non-obvious combinations of benign knowledge. Even if creating a classifier is computationally similar to unlearning, you're solving fundamentally different problems: (original framing) predicting emergent behaviors from raw data versus (new framing) suppressing already observed behaviors. With unlearning, you can iteratively refine until you achieve the desired behavior, then distill. With data filtering, you don't know the effects of your filtering until after training completes.
Claim: Computational efficiency is not the only value added from this work. Unlearn + distill requires significantly less labeled data than data filtering.
Rationale: Most unlearning procedures only use labels of a small fraction of the pretraining data. In our setup, it was less than 0.01% for language. This eases the data labeling requirement. At modern scales, the difference between labeling 0.01% vs 100% represents substantial annotation efforts. Note that we distilled on the whole pretraining data, but none of it was labeled. The suggestions about value heads or KV cache reuse are interesting optimizations worth exploring, though they don't address this fundamental labeling asymmetry.
Claim: Our robustness metric undersells the method's performance, though stronger attacks may exist.
Rationale: The adversary is extremely strong (best of 9 learning rates, 500 training steps, 8M tokens for language, 2M tokens for arithmetic). Even the oracle model (never trained on the forget domain) reaches 50% performance under this attack in arithmetic tasks.
Separately, while 30% compute for 50% robustness (compared to data filtering) isn't cheap, this tradeoff didn't exist before. The value add of UNDO over Unlearn-and-Distill is that it provides a tunable compute/robustness knob between the conventional unlearning and full reinitialization/data filtering