mlsanityData to 14 Oct 2026

AttnLink: Turning Attention into Schema Links for Text-to-SQL

arXiv 2608.00693 ↗First posted 1 Aug 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Schema linking is a critical component of Text-to-SQL systems, but existing approaches often trade off contextual modeling capacity, score-based controllability, and inference efficiency. We introduce AttnLink, an attention-based framework that converts LLMs' internal attention into continuous relevance scores for schema items. AttnLink extracts the attention from the generation-start position to candidate schema spans, enabling all candidates to be ranked in a single prefill pass without autoregressive decoding. We develop two variants: AttnLink-U, which directly probes pretrained attention without parameter updates, and AttnLink-S, which aligns the attention distribution with gold schema items through direct supervision. To improve coverage of multiple relevant schema items, AttnLink-S combines a set-mass objective with an adaptive probability-floor regularizer. The resulting scores support post-hoc precision-recall control through temperature scaling and cumulative-mass selection. Experiments on Spider, BIRD, and Spider2-SQLite show that AttnLink-S achieves mAP scores of 99.22%, 95.95%, and 83.29%, respectively, with millisecond-scale schema-linking latency. It also yields the best or tied-best execution accuracy for downstream SQL generation in seven of nine generator-dataset settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 25 references that are in the map. First posted on arXiv 1 Aug 2026.

Builds on

22 of 25 references.

References · 22

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  4. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 1,003
  5. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  6. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  7. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  8. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  9. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
  10. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  11. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  12. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
10 more
  1. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
  2. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 91
  3. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  4. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 52
  5. 2024Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankerscited by 43
  6. 2025Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-rankingcited by 31
  7. 2025LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLcited by 29
  8. 2024How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learningcited by 18
  9. 2025JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Samplingcited by 4
  10. 2026vLLM Hook v0: A Plug-in for Programming Model Internals on vLLMcited by 4

Built on by

Not cited yet.