做LLM对齐的团队终于有了一个不牺牲通用能力的干预方案——MARI用多适配器和能量门控解决了“一刀切”干预的痛点，做安全对齐或事实性增强的开发者可以直接试。
现有的大语言模型对齐方法通常对所有输入使用固定的干预方向与强度，导致在良性输入上通用能力下降。本文提出MARI（Multi-Adapter Representation Interventions via Energy Calibration），通过竞争性多适配器机制让不同专家捕获非线性校正模式，自适应决定干预方向与强度。同时设计基于能量的门控模块，利用内部传播动力学区分适合干预的输入。实验表明，MARI在TruthfulQA、BBQ和安全基准上达到最先进对齐性能，同时在MMLU和ARC等通用任务上保持甚至提升能力。代码已开源。
Multi-Adapter Representation Interventions via Energy Calibration
Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weights. Existing methods typically apply a fixed intervention uniformly across all inputs. However, we find that the appropriate intervention direction and strength vary substantially across samples, and such indiscriminate intervention leads to degradation of general capabilities on benign inputs. To address these challenges, we propose Multi-Adapter Representation Interventions via Energy Calibration (MARI). Specifically, we introduce a competitive multi-adapter mechanism in which specialized experts capture non-linear correction patterns and adaptively determine the appropriate intervention direction and strength for different samples. Furthermore, we design an energy-based gating module that leverages internal propagation dynamics to distinguish inputs that are applicable for intervention. Extensive experiments across diverse model families and parameter scales demonstrate that MARI achieves state-of-the-art alignment performance. Our method significantly improves performance on TruthfulQA, BBQ, and safety benchmarks, while maintaining and even improving general capabilities on tasks such as MMLU and ARC. Our code is available at https://github.com/V1centNevwake/MARI.