EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
Year: 2026
Type: preprint
Abstract: Schema linking is a difficult and important step in large-scale Text-to-SQL, where systems must identify a compact yet sufficient schema context from large and ambiguous databases. Existing methods often treat schema linking as deterministic selection around a single SQL path, but complex questions may admit multiple valid realizations with different schema needs. We reframe schema linking as uncertainty-aware schema-need inference over multiple plausible SQL paths, where the system distinguishes required schema items from path-dependent uncertain ones and acquires evidence only where needed. We instantiate this reframing with EviLink, which combines multi-hypothesis schema grounding with uncertainty-guided evidence acquisition. Experiments on BIRD-Dev and Spider2-Snow show that this perspective improves the balance among schema completeness, schema relevance, and token cost. On Spider2-Snow, EviLink achieves 93.04% field-level strict recall rate, uses 116.55K average tokens, and improves downstream SQL generation under a fixed generator.
Source: arXiv (Cornell University)
Authors: Zheng, Huawei, Yang, Sen, Yang, Zhaorui, Zhang, Yuhui, Feng, Haozhe, Li, Haoxuan, Yi, Xuan, Hu, Chao, Xie, Defeng, Hou, Chen, Huang, Danqing, Chen, Wei, Chen, Peng, Deng, Dazhen
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7162750310
Cites:
Cited by:
Related to: