Pith. sign in

REVIEW 12 cited by

RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.04942 v5 pith:OYSBL5TG submitted 2019-11-10 cs.CL cs.AI

Bailin Wang , Richard Shin , Xiaodong Liu , Oleksandr Polozov , Matthew Richardson This is my paper · ORCID
classification cs.CLcs.AI
keywords databaseschemaencodinglinkingalignmentframeworkquestionsrat-sql
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database schemas. The generalization challenge lies in (a) encoding the database relations in an accessible way for the semantic parser, and (b) modeling alignment between database columns and their mentions in a given query. We present a unified framework, based on the relation-aware self-attention mechanism, to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder. On the challenging Spider dataset this framework boosts the exact match accuracy to 57.2%, surpassing its best counterparts by 8.7% absolute improvement. Further augmented with BERT, it achieves the new state-of-the-art performance of 65.6% on the Spider leaderboard. In addition, we observe qualitative improvements in the model's understanding of schema linking and alignment. Our implementation will be open-sourced at https://github.com/Microsoft/rat-sql.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses

    cs.DB 2026-08 conditional novelty 6.0 of 10

    A verification-harness LLM system recovers column semantics from values alone, but its measured advantage over a direct LLM is selective abstention, not better prose, and a code-enforced gate makes that abstention bac...

  2. TailorSQL: An NL2SQL System Tailored to Your Query Workload

    cs.DB 2025-05 conditional novelty 6.0 of 10

    Adding workload-derived hints and tailored retrieval from past SQL queries improves NL2SQL execution accuracy and reduces prompt size on three benchmarks.

  3. ODIN: A NL2SQL Recommender to Handle Schema Ambiguity

    cs.DB 2025-05 conditional novelty 6.0 of 10

    ODIN uses schema masking, conformal-prediction filtering, and user-preference hints to return a small set of SQL queries that includes the correct one more often than baseline sampling on ambiguous-schema benchmarks.

  4. LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data

    cs.DB 2025-01 conditional novelty 6.0 of 10

    LEAP, an LLM-based library, automatically selects ML functions and writes SQL-like code to answer 92% of 120 social science queries over unstructured data on the first attempt, and 100% within three attempts.

  5. PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning

    cs.AI 2025-09 reject novelty 5.0 of 10

    PaVeRL-SQL reports SOTA execution accuracy on Spider2.0-SQLite using partial-match rewards and verbal RL, but overclaims SOTA on Spider and BIRD.

  6. ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration

    cs.CL 2025-02 conditional novelty 5.0 of 10

    An agentic Text-to-SQL pipeline using schema compression, self-refinement, majority voting, and selective column exploration reports state-of-the-art execution accuracy on Spider 2.0: 35.83 on Snow and 36.56 on Lite.

  7. EICopilot: Search and Explore Enterprise Information over Large-scale Knowledge Graphs with LLM-driven Agents

    cs.IR 2025-01 conditional novelty 5.0 of 10

    EICopilot uses LLM agents with in-context learning and entity masking to generate Gremlin queries for enterprise knowledge graph search, reporting better accuracy than zero-shot baselines on 150 internal queries.

  8. A Plug-and-Play Natural Language Rewriter for Natural Language to SQL

    cs.DB 2024-12 conditional novelty 5.0 of 10

    A multi-agent LLM module that checks, reflects on, and rewrites flawed questions yields small average execution-accuracy gains (1.6% Spider, 2.0% BIRD) on NL2SQL dev sets.

  9. Confidence Estimation for Text-to-SQL in Large Language Models

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    Consistency-based methods are the most reliable confidence signal for text-to-SQL in black-box LLMs, and executing queries against a database adds a useful correctness signal.

  10. Interactive Text-to-SQL via Expected Information Gain for Disambiguation

    cs.DB 2025-07 reject novelty 4.0 of 10

    An interactive text-to-SQL framework selects clarification questions by expected information gain over a distribution of candidate SQL queries.

  11. eSapiens: A Real-World NLP Framework for Multimodal Document Understanding and Enterprise Knowledge Processing

    cs.IR 2025-06 conditional novelty 3.0 of 10

    eSapiens combines text-to-SQL and hybrid retrieval-augmented generation with citation verification, and its evaluation on RAGTruth shows better contextual relevance than a FAISS baseline across most LLMs, at the cost ...

  12. A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges

    cs.AI 2024-12 conditional

    A high-level review of benchmarks, models, applications, and challenges in LLM-based text-to-SQL, with no new experiments or methods.

Pith tools