用密码模型测试AI能力挖掘技术，发现微调最有效。
The Elicitation Game: Evaluating Capability Elicitation Techniques
- 设计密码隐藏能力的模型，模拟真实能力挖掘场景。
- 提示词可激活普通密码模型，但无法触发新型抗挖模型。
- 代码生成任务中仅微调能唤醒隐藏能力，建议优先使用。
为准确评估可能部署或进一步开发的AI系统能力，需有效的能力评估方法。然而，许多原本隐藏的能力在模型发布后长期未被发现。为此，本文通过故意训练带有隐藏能力的模型生物（语言模型），其能力仅在输入特定密码时显现，以评估能力挖掘技术的有效性。提出一种基于电路断裂的新方法训练模型生物，比传统密码锁模型更具抗挖掘鲁棒性。研究聚焦于提示词和激活调控技术，并与微调方法对比。在多选题问答（MCQA）任务中，提示词可成功激发密码锁及电路断裂模型的能力，而激活调控无效；在代码生成任务中，仅微调能唤醒新型模型的隐藏能力。结果还表明，组合技术提升挖掘效果，但若可行，微调仍是提升评估可信度的首选方法。
原文摘要 · Abstract (English)
Capability evaluations are required to understand and regulate AI systems that may be deployed or further developed. Therefore, it is important that evaluations provide an accurate estimation of an AI system's capabilities. However, in numerous cases, previously latent capabilities have been elicited from models, sometimes long after initial release. Accordingly, substantial efforts have been made to develop methods for eliciting latent capabilities from models. In this paper, we evaluate the effectiveness of capability elicitation techniques by intentionally training model organisms -- language models with hidden capabilities that are revealed by a password. We introduce a novel method for training model organisms, based on circuit-breaking, which is more robust to elicitation techniques than standard password-locked models. We focus on elicitation techniques based on prompting and activation steering, and compare these to fine-tuning methods. Prompting techniques can elicit the actual capability of both password-locked and circuit-broken model organisms in the MCQA setting, while steering fails to do so. For a code-generation task, only fine-tuning can elicit the hidden capabilities of our novel model organism. Additionally, our results suggest that combining techniques improves elicitation. Still, if possible, fine-tuning should be the method of choice to improve the trustworthiness of capability evaluations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。