{"ID":2921670,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T05:56:00.181519634Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01148","arxiv_id":"2606.01148","title":"Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales","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 under a shared counterfactual simulation setting, using an LLM judge as predictor and measuring whether it can better predict a model's answers to follow-up questions when given its explanation. Across multiple instruction-tuned models, we analyze how explanation source, verbalization strategy, and feature granularity affect the simulatability of explanations. Our results show that explanation format and granularity affect simulatability: attribution-based explanations and self-generated rationales differ in how much they improve counterfactual prediction, with effects that vary across models and formats.","short_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 rational...","url_abs":"https://arxiv.org/abs/2606.01148","url_pdf":"https://arxiv.org/pdf/2606.01148v1","authors":"[\"Pingjun Hong\",\"Benjamin Roth\"]","published":"2026-05-31T10:35:35Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}