不重训练就能精细调控大模型对敏感话题的拒绝行为。
Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
- 用大模型当裁判给拒绝行为打分，再计算精准控制向量。
- 在4B和80B模型上移除政治敏感拒绝，安全基准测试表现接近基线。
- 可反向启用特定拒绝，适合需要可控内容过滤的场景。
我们提出Refusal Steering，一种无需重训练即可在推理阶段精细调控大模型对政治敏感话题拒绝行为的方法。该方法将脆弱的模式识别式拒绝检测替换为由大模型担任裁判的拒绝置信度评分机制，并提出岭正则化变体以计算更精确的控制向量，有效分离拒绝-合规方向。在Qwen3-Next-80B-A3B-Thinking模型上，该方法成功消除政治敏感话题上的拒绝行为，同时保持JailbreakBench上的安全性，通用基准性能接近基线。该方法在4B与80B模型间具有泛化能力，亦可按需诱导特定拒绝。我们分析了控制向量发现，拒绝信号集中于Transformer深层且分布于多个维度。结果表明，激活控制可在保留有害内容安全对齐的同时移除政治拒绝行为，为推理阶段提供可解释、可控制的内容治理路径。
原文摘要 · Abstract (English)
We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection with an LLM-as-a-judge that assigns refusal confidence scores and we propose a ridge-regularized variant to compute steering vectors that better isolate the refusal--compliance direction. On Qwen3-Next-80B-A3B-Thinking, our method removes the refusal behaviour of the model around politically sensitive topics while maintaining safety on JailbreakBench and near-baseline performance on general benchmarks. The approach generalizes across 4B and 80B models and can also induce targeted refusals when desired. We analize the steering vectors and show that refusal signals concentrate in deeper layers of the transformer and are distributed across many dimensions. Together, these results demonstrate that activation steering can remove political refusal behaviour while retaining safety alignment for harmful content, offering a practical path to controllable, transparent moderation at inference time.
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。