Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Structural Collapse of Safety-Critical Weight Protection Scorers Under Group-Wise Post-Training Quantization

AbstractPost-training quantization (PTQ) of instruction-tuned LLMs to 3 bits often destroys safety alignment, motivating safety-protection methods that keep a small budget of "safety-critical" weight blocks in full precision. We give a theoretical account of the many scoring rules proposed to choose those blocks. We prove that under symmetric group-wise PTQ the Taylor (SSMP) scorer concentrates to the gradient magnitude times a per-group constant; the gradient-times-weight (SNIP) scorer is empirically near-identical, so the entire compound family 𝛼|g⋅ w|+𝛽|g⋅𝛿 w| collapses to a single block ranking (worst-case Spearman 0.9971), and only pure magnitude or pure Fisher selects different blocks. We further show that recovered refusal behavior under small budgets is decoupled from the underlying safety mechanism: refusal can be restored while capability, adversarial robustness, and over-refusal balance stay at the unprotected level; at 3 bits heuristic attack metrics conflate incoherence with harm; and on weakly-aligned models protection raises classifier-judged attack success above the unprotected floor. Experiments on five open-weight 8–9B models across 110 conditions, including classifier-judged GCG and PAIR attacks and activation-level analysis, confirm every prediction; a four-category classification predictable from one baseline metric explains the cross-model variation. Code and configurations: https://github.com/jc-su/Safepress.

More from EMNLP 2026

All EMNLP 2026 papers →