Efficient Uncertainty Estimation for LLM-based Entity Linking in Tabular Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918152897560576 |
|---|---|
| author | Bono, Carlo Belotti, Federico Palmonari, Matteo |
| author_facet | Bono, Carlo Belotti, Federico Palmonari, Matteo |
| contents | Linking textual values in tabular data to their corresponding entities in a Knowledge Base is a core task across a variety of data integration and enrichment applications. Although Large Language Models (LLMs) have shown State-of-The-Art performance in Entity Linking (EL) tasks, their deployment in real-world scenarios requires not only accurate predictions but also reliable uncertainty estimates, which require resource-demanding multi-shot inference, posing serious limits to their actual applicability. As a more efficient alternative, we investigate a self-supervised approach for estimating uncertainty from single-shot LLM outputs using token-level features, reducing the need for multiple generations. Evaluation is performed on an EL task on tabular data across multiple LLMs, showing that the resulting uncertainty estimates are highly effective in detecting low-accuracy outputs. This is achieved at a fraction of the computational cost, ultimately supporting a cost-effective integration of uncertainty measures into LLM-based EL workflows. The method offers a practical way to incorporate uncertainty estimation into EL workflows with limited computational overhead. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01251 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Uncertainty Estimation for LLM-based Entity Linking in Tabular Data Bono, Carlo Belotti, Federico Palmonari, Matteo Computation and Language Machine Learning Linking textual values in tabular data to their corresponding entities in a Knowledge Base is a core task across a variety of data integration and enrichment applications. Although Large Language Models (LLMs) have shown State-of-The-Art performance in Entity Linking (EL) tasks, their deployment in real-world scenarios requires not only accurate predictions but also reliable uncertainty estimates, which require resource-demanding multi-shot inference, posing serious limits to their actual applicability. As a more efficient alternative, we investigate a self-supervised approach for estimating uncertainty from single-shot LLM outputs using token-level features, reducing the need for multiple generations. Evaluation is performed on an EL task on tabular data across multiple LLMs, showing that the resulting uncertainty estimates are highly effective in detecting low-accuracy outputs. This is achieved at a fraction of the computational cost, ultimately supporting a cost-effective integration of uncertainty measures into LLM-based EL workflows. The method offers a practical way to incorporate uncertainty estimation into EL workflows with limited computational overhead. |
| title | Efficient Uncertainty Estimation for LLM-based Entity Linking in Tabular Data |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2510.01251 |