ALMANACS: A Simulatability Benchmark for Language Model Explainability

Understand

How do we measure the efficacy of language model explainability methods? While many explainability methods have been developed, they are typically evaluated on bespoke tasks, preventing an apples-to-apples comparison.

• To help fill this gap, we present ALMANACS, a language model explainability benchmark.
• ALMANACS scores explainability methods on simulatability, i.e., how well the explanations improve behavior prediction on new inputs.
• The ALMANACS scenarios span twelve safety-relevant topics such as ethical reasoning and advanced AI behaviors; they have idiosyncratic premises to invoke model-specific behavior; and they have a train-test distributional shift to encourage faithful explanations.