CNT:通过跨模型神经转移实现面向安全的功能重用
CNT: Safety-oriented Function Reuse across LLMs via Cross-Model Neuron Transfer
AI总结:
本文提出CNT方法,通过转移少量神经元实现LLM间安全功能重用,有效提升安全对齐和偏见消除效果,性能损失低于1%。
摘要:
本文提出CNT方法,通过转移少量神经元实现LLM间安全功能重用,有效提升安全对齐和偏见消除效果,性能损失低于1%。
英文摘要:
The widespread deployment of large language models (LLMs) calls for post-hoc methods that can flexibly adapt models to evolving safety requirements. Meanwhile, the rapidly expanding open-source LLM ecosystem has produced a diverse collection of models that already exhibit various safety-related functionalities. This motivates a shift from constructing safety functionality from scratch to reusing existing functionality from external models, thereby avoiding costly data collection and training procedures. In this paper, we present Cross-Model Neuron Transfer (CNT), a post-hoc method that reuses safety-oriented functionality by transferring a minimal subset of neurons from an open-source donor LLM to a target LLM. By operating at the neuron level, CNT enables modular function-level adaptation, supporting both function addition andfunction deletion. We evaluate CNT on seven popular LLMs across three representative applications: safety disalignment, alignment enhancement, and bias removal. Experimental results show that CNT achieves targeted safety-oriented functionality transfer with minimal performance degradation (less than 1% for most models), consistently outperforming five baselines, demonstrating its generality and practical effectiveness.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。