通过动态控制安全适配器强度，实现模型安全与性能的平衡。
CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
- 用连续门控机制调节安全适配器激活强度，仅对有害输入响应干预。
- 在Llama-3-8B上将有害输出率从32.3%降至0.5%，且保持高基准性能。
- 适合需兼顾安全性和任务准确性的实际部署场景，如客服、教育等。
提升大语言模型（LLMs）安全性常以牺牲实用性为代价，因全局安全微调会影响有害与良性输入的响应。本文提出连续潜在适配器路由（CLEAR），一种条件化安全适配框架，利用轻量级隐藏状态门控机制连续调节安全低秩适配器的激活强度。该方法旨在减少有害输出，同时避免对冻结主干网络的不必要修改，从而防止良性提示下的性能下降。在多个常用安全与实用性基准测试中，CLEAR在提升HarmBench鲁棒性的同时，显著降低全局安全微调（如SFT或标准低秩适配，LoRA）带来的实用性损失。在Llama-3-8B-Instruct上，CLEAR将HarmBench ASR从32.3%降至0.5%，并保留大部分基础模型性能，相比全局SFT或LoRA，GSM8K准确率最高提升7.1个百分点。结果表明，CLEAR是改善大模型对齐中安全-实用性权衡的有力方案。
原文摘要 · Abstract (English)
Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safety tuning may affect model responses to both harmful and benign inputs. We propose \textbf{C}ontinuous \textbf{L}at\textbf{E}nt \textbf{A}dapter \textbf{R}outing (CLEAR), a conditional safety adaptation framework that uses a lightweight hidden-state gate to continuously control the activation strength of a safety low-rank adapter. CLEAR aims to reduce harmful completions while avoiding unnecessary changes to the frozen backbone that could degrade performance on benign prompts. Experiments on widely used safety and utility benchmarks show that CLEAR improves robustness on HarmBench while reducing the utility degradation observed with globally applied safety tuning such as SFT or standard low-rank adaptation (LoRA). On Llama-3-8B-Instruct, CLEAR reduces HarmBench ASR from 32.3\% to 0.5\%, while retaining most of the base model's utility and achieving up to 7.1 percentage points higher GSM8K accuracy than globally applied SFT or LoRA. These results suggest that CLEAR is a promising mechanism for improving the safety--utility trade-off in LLM alignment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。