EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
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_ | 1866917543359283200 |
|---|---|
| author | Zheng, Huawei Yang, Sen Yang, Zhaorui Zhang, Yuhui Feng, Haozhe Li, Haoxuan Yi, Xuan Hu, Chao Xie, Defeng Hou, Chen Huang, Danqing Chen, Wei Wu, Yingcai Chen, Peng Deng, Dazhen |
| author_facet | Zheng, Huawei Yang, Sen Yang, Zhaorui Zhang, Yuhui Feng, Haozhe Li, Haoxuan Yi, Xuan Hu, Chao Xie, Defeng Hou, Chen Huang, Danqing Chen, Wei Wu, Yingcai Chen, Peng Deng, Dazhen |
| contents | 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 90.15% field-level strict recall rate, uses 123.30K average tokens, and improves downstream SQL generation under a fixed generator. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29670 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL Zheng, Huawei Yang, Sen Yang, Zhaorui Zhang, Yuhui Feng, Haozhe Li, Haoxuan Yi, Xuan Hu, Chao Xie, Defeng Hou, Chen Huang, Danqing Chen, Wei Wu, Yingcai Chen, Peng Deng, Dazhen Computation and Language Artificial Intelligence 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 90.15% field-level strict recall rate, uses 123.30K average tokens, and improves downstream SQL generation under a fixed generator. |
| title | EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.29670 |