- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper proposes training safety classifiers that change their decisions when the given policy state changes. The paper introduces Boundary-Stable PolicyFlip to fine-tune models to match policy-state interventions. By constructing a pairwise ranking with a score center c, Boundary-Stable PolicyFlip optimizes the weaker-endpoint slack. Experimental results suggest that BS-PF improves Qwen3.5-4B balanced accuracy over pointwise training on a controlled policy-intervention benchmark.
Critical strengths
-
The paper performs good ablation controls. Pair-CE, PF+PairCE, and Boundary-only are important additions beyond comparing against training or ranking alone.
-
Experimental evaluations show that Boundary-Stable PolicyFlip improves the safeguard performance.
Critical weaknesses
-
The paper is hard to read and follow. As disclosed in the AI Use Statement, this paper is likely to be written by AI. I think the authors should rewrite the paper to improve readability. For example, what are BS-PF and BG-PF in your abstract? At least, the authors should write their full names the first time they are mentioned.
-
Improvements are not convincing for out-of-domain setups. On Policy OOD, Pair-CE has a higher mean BAcc than both proposed variants. These results fail to prove that Boundary-Stable PolicyFlip can generalize well.
-
No actual new policy semantics are tested even for the OOD setups. All four Boolean policy mappings remain fixed and are learned during training. For example, Policy OOD only changes cardinality and code morphology, while Attack OOD only changes wording.
Questions for authors
-
What is a softplus function? I cannot see any explanation of it in this paper.
-
I tried to follow your formulations in Sec. 2, but I cannot understand your derivations. Could you update your writing to provide more details?
-
Can you provide more details on Policy-state benchmark construction?
Thank you for the questions about the derivation and benchmark construction, and for highlighting the scope of the OOD evaluation. We have rewritten the abstract and opening sections to start with the safety problem rather than the notation: the same operation may become unsafe when its authorization is revoked, even though the governing rule does not change. Table 1 follows this before-and-after intervention, and Appendix A.3 provides the fixed system instruction and both complete model-visible user messages. The revised benchmark description also explains the roles of the compiler, renderer, and EventIR.
The key distinction behind the method is between correctly ranking a safe/unsafe pair and giving both endpoints the correct verdict. For example, the score pairs (1, 3) and (-1, 1) have the same ranking gap, but only the second crosses the zero threshold correctly. Moving both scores together can preserve their order while changing the decisions. Let d_safe and d_unsafe be the unsafe-minus-safe scores, with gap g = d_unsafe - d_safe and center c = (d_unsafe + d_safe)/2. A correct flip requires g > 2|c|, which gives the weaker-endpoint slack b = g/2 - |c| = min(-d_safe, d_unsafe). Using the standard softplus function, softplus(t) = log(1 + exp(t)), the boundary term becomes softplus(-b) = max(CE_safe, CE_unsafe) at the default settings (Eq. 9). The methodological step is to use this crossing-derived limiting endpoint to allocate supervision: BS-PF combines that signal with ranking, while BG-PF adjusts the ranking weight according to boundary placement. Neither changes inference.
The benchmark contains 4,608 training programs and 768 programs per raw evaluation split. Each program fixes a policy profile and event, varies the relevant trusted registry state, and obtains exact safe/unsafe labels from one of four Boolean policy functions. The resulting examples are rendered into model inputs without revealing the gold labels. Policy OOD changes registry size and identifier morphology; Attack OOD uses held-out mechanism contexts; Tool OOD uses the held-out tool-call surface. The governing functions remain unchanged, so these splits isolate a guard's response to state and representation changes rather than introducing a different rule definition.
The revised results connect this setting to the training objectives. On raw Policy OOD, BS-PF improves Direction over PF+PairCE by 4.08 points (95% CI [2.69, 5.47]). On independently rendered External-B inputs, BG-PF improves PairExact over matched Pair-CE by 2.30 points and Direction by 5.25 points (95% CI [3.04, 7.42]). The program-aligned analysis finds 280 corrected versus 227 regressed pairs (Table 5 and Appendix Table 16). PairExact requires both endpoint decisions to be correct, making it a direct measure of the crossing behavior that motivated the objective.