Year: 2026
Type: conference-paper
Abstract: Simulatability is an evaluation protocol for explanations that quantifies their usefulness by how well they help a user predict a task model's outputs.Since human evaluation is costly, automated simulatability replaces human explainees with LLM simulators, as proposed in ConSim (Poché et al., 2025) for large-scale experiments.We qualitatively replicate and extend ConSim's ranking of explanation methods across the tested datasets, explanation families, and simulator LLMs, and identify two limitations.First, when class names are meaningful, simulators can obtain high simulatability by solving the classification task directly, without relying on the explanations.Second, class anonymization can reward explanations for leaking the hidden label mapping, a limitation we expose with a new classes-as-concepts baseline.These results are consistent with a shortcut hypothesis: in the tested settings, simulator predictions mainly rely on task priors, while explanations produce small changes.We derive recommendations for more robust automated simulatability evaluations.
Institutions: Institut de Recherche en Informatique de Toulouse, IRT Saint Exupéry, Université de Toulouse, University of Groningen, German Research Centre for Artificial Intelligence, Berlin Institute for the Foundations of Learning and Data, Technische Universität Berlin, Centre National de la Recherche Scientifique
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7212072012