{"ID":2921713,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T05:56:00.181519634Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01210","arxiv_id":"2606.01210","title":"Can we trust LLM Self-Explanations for Entity Resolution?","abstract":"Large Language Models (LLMs) have recently shown strong performance on Entity Resolution (ER). Additionally, akin to their prowess in providing accurate predictions, these models often generate self-explanations alongside their predictions through prompting. While such self-explanations are appealing due to their negligible computational cost, their actual reliability remains largely unexplored. In this paper, we present the first large-scale systematic evaluation of LLM self-explanations for ER, focusing on feature attribution and counterfactual explanations at both the attribute and token levels. Across three LLMs, ten datasets, and multiple prompting strategies, we show that self-explanations are often unstable, weakly faithful, and poorly aligned with counterfactual evidence, revealing a substantial gap between plausibility and causal relevance. We further demonstrate that established post-hoc explanation methods provide significantly higher trustworthiness, but at a prohibitive computational cost when applied to LLMs. To bridge this gap, we introduce \\uncerta{}, a hybrid explanation framework that leverages self-explanations as priors to guide post-hoc exploration. \\uncerta{} achieves explanation quality comparable to post-hoc methods while reducing cost by up to an order of magnitude.","short_abstract":"Large Language Models (LLMs) have recently shown strong performance on Entity Resolution (ER). Additionally, akin to their prowess in providing accurate predictions, these models often generate self-explanations alongside their predictions through prompting. While such self-explanations are appealing due to their negli...","url_abs":"https://arxiv.org/abs/2606.01210","url_pdf":"https://arxiv.org/pdf/2606.01210v1","authors":"[\"Tommaso Teofili\",\"Donatella Firmani\",\"Nick Koudas\",\"Paolo Merialdo\",\"Divesh Srivastava\"]","published":"2026-05-31T13:00:57Z","proceeding":"cs.DB","tasks":"[\"cs.DB\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}