New frontier models have developed the capability of eval-awareness, putting the utility of evals at risk. But what do people really mean when they say “a model is eval-aware?” In this post, I try to disentangle this statement and offer my views on the different concepts it entails.

When people say “model X is eval-aware”, I believe what they generally mean is “model X can tell when a task belongs to an evaluation, leading it to change its behaviour and propensities”.^[1] Thus, this statement makes three claims about the model;

The model can tell when a task belongs to an evaluation, i.e. $P_{e v a l}^{M} (x | x \in D_{e v a l}) > 0.5$
The model changes policy based on context, i.e. $π_{e v a l}^{M} \neq π_{d e p l o y}^{M}$
The model uses the knowledge (in claim 1) to implement different policies (in claim 2).

Redefining the terms.

Claim 1, in its purity, is evaluation awareness (in the real sense of the word). It is the model's ability to identify evaluation tasks. Eval-aware models can tell that a task belongs to evaluation above random chance.
Claim 2 is evaluation invariance: the degree to which the model changes in propensities and behaviour when it thinks it’s being evaluated. Eval-invariant models apply the same policy during evaluation and deployment.

Next, it is assumed that the eval-aware models are not eval-invariant (claim 3). There is a good reason for this: the most eval-aware models (e.g., Claude Sonnet 4.5) are indeed not eval-invariant, i.e., their evaluation scores change when they are steered out of awareness.

The assumption that eval-aware models cannot be eval-invariant has been shaping current solutions to the root problem: we want the learnings from model evaluations to hold when they are deployed and generalise to real-world scenarios. Consider, for example, that our current solutions primarily target awareness. They either try to approximate an eval-unaware model by steering or modifying their chain of thought, or by creating “more realistic evaluations”.

However, IMO it is possible for a model to be eval-aware AND eval-invariant, i.e., there can exist a model that doesn’t change its behaviour or propensities despite thinking it’s being evaluated.^[2] The causal effect that awareness has on model behaviour can be cut.

Factorising the current meaning of eval-awareness into its subcomponents like this is important because it opens doors to new solutions as it offers...

Posts

Wikitag Contributions

Comments