pacchu78
No user record in our sample, but pacchu78 has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
No user record in our sample, but pacchu78 has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
Yes, that was the initial hypothesis, which has been proven and shown conclusively to be true. If this was straightforward, then we should be more careful and do more tests when using fine-tuned models.
Hi, I am one of the authors of the paper. The previous works on fine-tuning and vulnerabilities fine-tuned a model to produce toxicity using ~10 samples and showed that even small samples would break the alignment. The…