潜在人格对齐：无需提及危害的改进
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
AI总结：
本文提出LPA方法，通过训练抽象人格特质提升模型鲁棒性，以少样本实现高防御效果，且在六个危害基准测试中表现更优。
摘要：
当前大语言模型的对抗鲁棒性方法需要大量有害提示数据（数千到数万例），但仍易受新攻击向量和分布偏移影响。我们提出潜在人格对齐（LPA），一种样本高效的防御方法，通过训练抽象人格特质而非具体有害行为来实现鲁棒性。使用少于100个特质陈述和潜在对抗训练，LPA在训练150k+示例的方法上达到可比的攻击成功率，同时保持优越的实用性。关键的是，LPA在未见过的攻击分布上泛化能力更强，将误分类率降低2.6倍，比基线方法在六个危害基准测试中表现更优——在训练过程中从未见过有害示例。我们的结果表明，基于人格的对齐提供了一种构建鲁棒防御的原理性方法，成本低廉。
英文摘要：
Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We propose Latent Personality Alignment (LPA), a sample-efficient defense that achieves robustness by training models on abstract personality traits rather than specific harmful behaviors. Using fewer than 100 trait statements and latent adversarial training, LPA achieves comparable attack success rates to methods trained on 150k+ examples, while maintaining superior utility. Critically, LPA generalizes better to unseen attack distributions, reducing misclassification rates by 2.6x compared to baseline across six harm benchmarks -- without ever seeing harmful examples during training. Our results demonstrate that personality-based alignment offers a principled approach to building robust defenses with minimal cost.
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。
