Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales 事件

Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales arXiv:2606.01148v1 Announce Type: new Abstract: Natural-language explanations are often treated as a unified interface for understanding model behavior, but different explanation sources may support simulation in different ways. This paper compares two families of explanations for question answering models: verbalized feature attributions and self-generated rationales. We evaluate them