- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes LCID (Linear-to-Causal Interventional Disentanglement) for preserving safety during downstream fine-tuning of large language models. LCID decomposes the model into shared, task-private, and safety-private components, and uses branch-removal interventions to measure each private component’s intended contribution and its influence on the other function. Its training objective suppresses cross-effects, preserves target contributions, and anchors the complete model to the original safety-aligned model. Evaluation covers Qwen3-4B, Llama-3.1-8B, and GLM-4-9B, using GSM8K, MBPP, and IFEval for utility and AdvBench, BeaverTails-H, and StrongREJECT for safety. Additional analyses examine parameter geometry, intervention effects, and prompt-level safety changes. The authors report improved safety–utility trade-offs and reduced functional interference relative to the evaluated baselines.
Critical strengths
-
A concrete formulation of functional disentanglement. The paper distinguishes parameter-space orthogonality from functional independence and operationalizes this distinction through controlled task/safety branch interventions. Measuring and explicitly suppressing cross-functional effects provides a useful framework for studying and reducing interference between downstream capability and safety.
-
Promising reported safety–utility trade-off. On Qwen3-4B, LCID achieves a lower average unsafe-response rate than GuardSpace (4.09% versus 8.50%), with comparable average utility (71.39% versus 71.27%). These aggregate results suggest practical potential for preserving safety during downstream adaptation and provide the strongest empirical support for the proposed approach.
Critical weaknesses
1. Limited coverage of recent, closely related work. The related-work discussion and experimental comparisons do not adequately cover recent advances in safety-preserving fine-tuning. Two particularly relevant omissions are Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks (SBR, ICML 2026) and Jailbreak to Protect (ICML 2026). Comparisons with these methods would help establish LCID’s additional benefit beyond safety anchoring and existing modular adaptation strategies, respectively. Please discuss these connections and include comparisons under matched task data, safety supervision, and comparable training budgets.
2. Incomplete baseline coverage across backbones. Table 1 provides the full baseline comparison only for Qwen3-4B. For Llama-3.1-8B and GLM-4-9B, the reported results compare only Orth. and LCID, omitting the external baselines evaluated on Qwen. This limits the evidence that LCID’s advantage over existing methods generalizes across model families. Please extend the comparison with at least one key external baseline to these two backbones, or qualify the corresponding claims.
3. Unclear and inconsistent figure reporting. Figure 5 requires clarification. Its middle-panel caption specifies a comparison from linear orthogonalization to LCID, whereas the annotated reductions repeat Figure 4’s reductions relative to standard fine-tuning. For example, Table 1 implies Orth.-to-LCID reductions of 68.67 and 57.66 percentage points for Llama and GLM, respectively, rather than the annotated 67.3 and 56.3. Furthermore, the right panel labels both target and cross-effects as JS effects, while Eq. (2) defines target effects as supervised-loss improvements. Please reconcile the comparison baselines and metric definitions, explain any differences in evaluation settings, and explicitly define the reported selectivity ratios.
Questions for authors
-
In Figure 5, are the unsafe-rate reductions computed relative to standard fine-tuning or Orth.? Please reconcile the caption and annotated reductions with Table 1.
-
Why are target effects reported as JS divergence in Figure 5, whereas Eq. (2) defines them as supervised-loss improvements? Please clarify the metric definitions and how the selectivity ratios are calculated.
-
Why does Table 1 compare only Orth. and LCID for Llama-3.1-8B and GLM-4-9B? Are comparable results against external baselines available to support the claimed advantage across model families?