- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes Adaptive Regularization (A-Reg) to curb safety degradation during LLM fine-tuning. A frozen probe direction gives a per-token log-probability margin, which becomes an example-level control score and is combined with a reference-model token preference to set per-token SFT/KL loss weights before LoRA training. The method rests on the claim that pre-generation hidden states linearly predict safety outcomes.
Critical strengths
Testing identity-shifting and backdoor-trigger attacks is broader than evaluating only standard harmful SFT.
The data partitioning for probe fitting, direction selection, and evaluation is carefully designed and helps avoid leakage in the activation-probing pipeline.
Critical weaknesses
I am concerned about specific numbers that are bolded as wins when they are ties. In Table 1, Qwen2.5-3B-Instruct shows Surgery and A-Reg (Ours) bit-identical to two decimal places - yet A-Reg is the only one bolded, visually implying a win that does not exist. The same thing happens in Table 5: Phi-3.5-mini-instruct shows Surgery and A-Reg (Ours) , again bolded as if A-Reg wins when it is a tie. Two independent tables, two different metrics (ASR and GSM8K accuracy), and both times the ``winning'' bolded number is bit-identical to the strongest baseline, how do two separately-trained adapters land on the exact same value to two decimal places, and why bold one over the other?
The baseline set shown looks selective, and the strongest baseline disappears exactly where it matters most. Table 1 compares against five baselines, and Surgery is A-Reg's closest competitor there (it ties A-Reg on Qwen2.5-3B, vs.\ ). Table 2 drops SPARD and DSS entirely, keeping only Surgery; Tables 3 and 4 (identity-shifting and backdoor attacks, the hardest, most adversarial settings) drop Surgery too, leaving A-Reg compared only against vanilla SFT and C-SFT. Why does the strongest baseline disappear exactly in the two attack settings where its relative performance against A-Reg would be most informative?
The core assumption behind the per-token preference threshold is acknowledged as unrealistic in Section 3.3, but is not empirically tested. There is no analysis showing whether the trained model actually follows the target token distributions, nor an ablation testing cases where the single-token assumption is badly violated. Since the method's allocation rule relies on this assumption, this seems important to validate.
Questions for authors
What happened on Qwen2.5-7B HEx-PHI in Table 2? Transcription error, or a genuine failure mode?
Given Fig.\ 5, what does the adaptive per-token mechanism actually buy over the static grid-search optimum, across all four models and all of Tables 2-4?