- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies safety degradation during benign or poisoned fine-tuning through the geometry of utility and safety gradients. It proposes GraSafe, which precomputes a safety gradient, extracts a truncated left-singular subspace, estimates a curvature-induced change through a lookahead finite difference, and conditionally projects the acceleration and candidate gradient based on their inner products with the safety gradient. The experiments cover four downstream tasks, four harmful-data sources, and four model backbones, with safety and utility reported together. In many harmful fine-tuning settings, the reported results show substantial Harmful Score reductions relative to vanilla SFT while retaining task utility. The paper also includes a first-order comparison and sensitivity studies.
Critical strengths
-
The method addresses a relevant failure mode with broad empirical coverage across downstream tasks, harmful-data sources, sample sizes, poison ratios, and model families. Tables 1–5 show substantial Harmful Score reductions relative to SFT in many harmful fine-tuning settings. Reporting safety and downstream utility together makes the central trade-off visible, and many of the reported improvements are large.
-
The paper provides evidence beyond end-to-end comparisons. The gradient-cosine analysis motivates the design, and Figure 5 includes a relevant first-order projection variant that omits the curvature term. At the plotted matched nonzero k values, GraSafe appears to offer a better safety–utility trade-off in that experimental setting. The local Taylor analysis also provides a useful conditional explanation under its stated smoothness and small-step assumptions.
Critical weaknesses
-
The projection mechanism does not generally justify the claim that only safety-conflicting components are removed (Abstract, p. 1; Algorithm 1, p. 5; Eqs. 2–4, p. 6). The conflict test uses the full safety gradient, whereas the correction removes the entire component in a truncated leading left-singular subspace. For example, with G_s=diag(2,1), k=1, and candidate gradient G=diag(1,-3), the inner product changes from -1 to -3 after projection. Thus the written rule can remove an aligned component and increase conflict with the anchored safety gradient. This limits the general mechanism claim; it does not establish failure of the reported experiments. The paper should clarify the parameter layout and the conditions or empirical evidence supporting this approximation.
-
Several reporting ambiguities limit assessment of comparative performance. Under apparently matching default settings, Lisa-base has HS 38.20 in Tables 1–3 but 27.20 in Tables 4–5, with FA 73.50 throughout; Safe LoRA also has differing HS entries with identical FA. Table 2 prints a Lisa-base HS average of 25.36, although its displayed entries average to 27.56. These may reflect different runs, configurations, or reporting errors and require reconciliation. I also could not locate the exact HS evaluation protocol, the AlpacaEval scoring definition, or the default/selection rule for k in the manuscript. Figure 5 provides a useful first-order comparison in one setting, but without reported run-level uncertainty the reliability of the incremental curvature benefit remains unclear. The substantial improvements over SFT remain meaningful.
Questions for authors
-
What parameter layout does Unflatten use, and how is k selected? Could you clarify the projection claim in light of the example above, using appropriate conditions or before/after conflict measurements? Please also reconcile the final sentence of lines 263–267 with Algorithm 1's second conflict test.
-
Could you reconcile the repeated default-setting cells and the Table 2 average, identifying any differences in runs or evaluation configurations? Please specify the HS judge and evaluation set/protocol, including the denominator, and the metric reported for AlpacaEval.
-
For the Figure 5 setting, can you provide a matched-k repeated comparison of GraSafe and the first-order variant, with seeds and variability, to establish the reliability of the incremental curvature benefit?