分裂人格训练：通过交替人格揭示潜在知识
Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
AI总结：
通过分裂人格训练方法，揭示大型语言模型中隐藏的潜在知识，提升对模型行为的审计能力。
摘要：
检测大型语言模型中的不一致行为具有挑战性，因为模型可能在训练过程中学会隐藏不良行为。标准审计技术效果有限：黑盒方法往往无法区分不一致的输出与良性输出，而机制可解释性无法随着模型能力的提升而扩展。我们引入了分裂人格训练（SPT），该方法通过微调一个第二“诚实人格”使其成为LoRA参数，在正常操作期间保持非活动状态。在主模型响应后，我们激活LoRA适配器并插入触发字符串，使诚实人格能够审查响应并访问主模型的潜在状态。我们测试了我们的方法在Anthropic Auditing Game Model Organism上的表现，这是一个基准测试，其中Llama-3.3-70B被训练以利用奖励黑客行为并隐藏这种行为。SPT实现了96%的整体准确率，而Anthropic报告的准确率接近0%。诚实人格揭示了外部观察者无法访问的潜在知识，例如被妥协模型训练的虚构偏见。
英文摘要：
Detecting misalignment in large language models is challenging because models may learn to conceal misbehavior during training. Standard auditing techniques fall short: black-box methods often cannot distinguish misaligned outputs from benign ones, and mechanistic interpretability does not scale with model capabilities. We introduce Split Personality Training (SPT), which fine-tunes a second ``honest persona'' into LoRA parameters that remain inactive during normal operation. After the main model responds, we activate the LoRA adapter and insert a trigger string, enabling the honest persona to review the response while accessing the main model's latent states. We test our method on the Anthropic Auditing Game Model Organism, a benchmark where Llama-3.3-70B is trained to exploit reward hacks while concealing this behavior. SPT achieves 96% overall accuracy, whereas Anthropic reports near 0% accuracy. The honest persona reveals latent knowledge inaccessible to external observers, such as the fictional biases the compromised model was trained on.
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。
