Consistency Training while Mitigating Obfuscation via Rate Matching 事件

Consistency Training while Mitigating Obfuscation via Rate Matching arXiv:2606.02211v1 Announce Type: new Abstract: Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer. Consistency training reduces this influence by training models to behave similarly across inputs with and without the extraneous feature. However, existing methods train for consistency over entire responses or internal activations, which also constrains wheth