EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced Schema Linking with Large Language Models via Self-Verification and Value Hints

Linfei Ma, Dexing Wei, Xiangpeng Li, Feng Wen, Haisu Zhang

Big Data and Cognitive Computing · 31.03.2026 · 10 (4) · 104

DOI: 10.3390/bdcc10040104 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 31.03.2026. Verfasst von Linfei Ma und 4 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Schema linking, the task of identifying relevant database schema elements (tables and columns) for natural language queries, is a critical component in database-driven natural language interfaces. While existing approaches rely on question decomposition to handle complex queries, they often suffer from error propagation and low precision. In this paper, we propose a novel schema linking framework enhanced by self-verification (SV) and value hints (VHs) that significantly improves both precision and recall. Our approach introduces two key components: (1) self-verification (SV), an iterative refinement mechanism that validates and corrects initial predictions through explicit verification prompts, and (2) value hints (VHs), which explicitly guide the model to recognize database values mentioned in queries. We conduct comprehensive experiments on two benchmark datasets, Spider and BIRD, using two language models of 4B and 80B parameters. Our results demonstrate that SV + VH consistently improves performance across datasets, models, and method configurations, outperforming both decomposition-based approaches and compute-matched alternatives such as self-consistency under equivalent inference budgets.

Zitieren

APA

Ma, L., Wei, D., Li, X., Wen, F., & Zhang, H. (2026). Enhanced Schema Linking with Large Language Models via Self-Verification and Value Hints. Big Data and Cognitive Computing, 10(4), 104. https://doi.org/10.3390/bdcc10040104

Vancouver

Ma L, Wei D, Li X, Wen F, Zhang H. Enhanced Schema Linking with Large Language Models via Self-Verification and Value Hints. Big Data and Cognitive Computing. 2026;10(4):104. doi:10.3390/bdcc10040104

BibTeX
@article{Ma2026,
  author = {Ma, Linfei and Wei, Dexing and Li, Xiangpeng and Wen, Feng and Zhang, Haisu},
  title = {Enhanced Schema Linking with Large Language Models via Self-Verification and Value Hints},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {104},
  doi = {10.3390/bdcc10040104}
}
Kostenlos starten →