The Elicitation Game: Evaluating Capability Elicitation Techniques
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 an 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.
Code (1)
Tasks
Code GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Auditing Games for Sandbagging
Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagging detection techniques using an auditing game. First, a re…
Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systems
Recent approaches in Conversational Recommender Systems (CRSs) have tried to simulate real-world users engaging in conversations with CRSs to create more realistic testing environments that reflect the complexity of huma…
Recommendation SystemsUser SimulationThree Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation
To steer language models towards truthful outputs on tasks which are beyond human capability, previous work has suggested training models on easy tasks to steer them on harder ones (easy-to-hard generalization), or using…
Evaluating AI cyber capabilities with crowdsourced elicitation
As AI systems become increasingly capable, understanding their offensive cyber potential is critical for informed governance and responsible deployment. However, it's hard to accurately bound their capabilities, and some…
Eliciting Secret Knowledge from Language Models
We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to possess specific knowledge that they app…