Can we trust LLM Self-Explanations for Entity Resolution?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914621443538944 |
|---|---|
| author | Teofili, Tommaso Firmani, Donatella Koudas, Nick Merialdo, Paolo Srivastava, Divesh |
| author_facet | Teofili, Tommaso Firmani, Donatella Koudas, Nick Merialdo, Paolo Srivastava, Divesh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01210 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Can we trust LLM Self-Explanations for Entity Resolution? Teofili, Tommaso Firmani, Donatella Koudas, Nick Merialdo, Paolo Srivastava, Divesh Databases 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. |
| title | Can we trust LLM Self-Explanations for Entity Resolution? |
| topic | Databases |
| url | https://arxiv.org/abs/2606.01210 |