LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models
We study controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models, aiming to increase non-refusal target-response behavior while preserving general capability under a compact intervention footprint. Existing broad direction-based edits can perturb general-purpose computation, whereas support-only expert edits often lack sufficient capacity to correct heterogeneous refusal representations. To address this limitation, we introduce Localized Multidirectional Correction (LoMC), a support-gated intervention framework that follows a support-then-correction execution order: it first identifies a compact edit support, then aggregates prototype correction directions into layer-wise correction directions, and finally applies rank-one layer-wise correction only within the selected support. By using the edit support as a structural gating constraint, LoMC increases correction capacity without expanding the intervention scope. Experiments on text-only and multimodal safety benchmarks across four routed backbones show that LoMC substantially improves non-refusal target-response behavior while maintaining general capability under a compact intervention footprint.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
RepIt: Steering Language Models with Concept-Specific Refusal Vectors
Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simple and data-efficient framework for isolating concept-specific representa…
Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs
Large language models (LLMs) have shown strong performance across natural language tasks, but remain vulnerable to backdoor attacks. Recent model editing-based approaches enable efficient backdoor injection by directly m…
DiversityModel EditingSafety AlignmentSOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic interpretability, recent work encoded ref…
Refusal Beyond a Single Direction: A Preliminary Comparison of Diff-in-Means and INLP
Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the residual stream, recoverable by a difference-in-means (DiM) of harmful and harmless activations…
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair
While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that merely appear risky. We present DDOR (De…