# Can we trust LLM Self-Explanations for Entity Resolution?

arXiv: https://arxiv.org/abs/2606.01210 · HTML: https://mlsanity.com/paper/2606.01210/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2026.

## Built on by (most cited first, 1 of 1)

- [Beyond Scale and Generation: Understanding Language Model-based Entity Matching](https://mlsanity.com/paper/2607.24688/) (2026)

## Abstract (arXiv)

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.