arXivPaperNeeds Review

CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment

CLEAR conditionally activates a safety adapter instead of applying safety tuning to every prompt, reducing harmful completions while limiting benign-task degradation.

arXiv

Open Source Open Markdown Open JSON

Source Summary

**CLEAR** uses a hidden-state gate to vary the strength of a safety LoRA while keeping the backbone frozen. On Llama-3-8B-Instruct, HarmBench attack success fell from **32.3% to 0.5%**, with up to **7.1 points** more GSM8K accuracy than global SFT or LoRA.

Practical Implication

For builders serving specialized models, conditional adapter routing is worth evaluating when global safety tuning damages benign tasks. Test the gate, adapter, and untouched backbone as separate failure surfaces across both adversarial and ordinary workloads.

Agent-Ready Context

**CLEAR** uses a hidden-state gate to vary the strength of a safety LoRA while keeping the backbone frozen. On Llama-3-8B-Instruct, HarmBench attack success fell from **32.3% to 0.5%**, with up to **7.1 points** more GSM8K accuracy than global SFT or LoRA.

For builders serving specialized models, conditional adapter routing is worth evaluating when global safety tuning damages benign tasks. Test the gate, adapter, and untouched backbone as separate failure surfaces across both adversarial and ordinary workloads.

The results come from selected safety and utility benchmarks on **Llama-3-8B-Instruct**. They do not establish production robustness, routing reliability under distribution shift, or behavior on other model families.

Context Map

modelsecurity#model-selection#agent-reliability

Uncertainty

The results come from selected safety and utility benchmarks on **Llama-3-8B-Instruct**. They do not establish production robustness, routing reliability under distribution shift, or behavior on other model families.