Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering

Yuxuan Zhu, Tengjun Jin, Yoojin Choi, Daniel Kang · Mar 20, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Low trust

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

Abstract

Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research. Recent efforts have focused on improving accuracy by building increasingly complex multi-stage large LLM pipelines, layering task decomposition, schema linking, and model-based query selection on top of an LLM. Despite this growing complexity, a substantial gap (>10%) between such systems and human experts persists on benchmarks, suggesting that pipeline engineering alone has hit a ceiling. We show that human-level Text-to-SQL performance is achievable by fine-tuning an LLM using RLVR on clean data, without pipeline components. In this paper, we identified the dominant bottleneck for RLVR on Text-to-SQL: existing training data contains pervasive annotation errors that mislead optimization. To address this, we developed a multi-round, expert-driven verification pipeline and used it to curate BIRD-Platinum, a dataset of 2.5k verified instances sampled from BIRD Train, with errors corrected in 61% of instances. We show that fine-tuning Qwen3-235B on BIRD-Platinum yields consistent improvements (11-16%) over BIRD Train on Arcwise-Plat (an expert-verified version of BIRD) and Spider2, outperforming SOTA open-source systems by 0.6-16%. Furthermore, we diagnosed two failure modes of standard RLVR on Text-to-SQL. We find that (1) result-based rewards have non-trivial false positive rates, and (2) models systematically ignore the external knowledge in BIRD-style problems. To address them, we propose ReViSQL-BIRD, a specialized reward shaping method that combines result-based rewards with SQL equivalence verification and leverages process rewards for incentivizing external-knowledge use. We fine-tuned Kimi-K2.6 with ReViSQL-BIRD. On Arcwise-Plat, ReViSQL-BIRD-K2.6 is the first method to achieve human-level accuracy (92.96%), outperforming top five open-source systems by 9-22%.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

  • This paper looks adjacent to evaluation work, but not like a strong protocol reference.
  • The available metadata is too thin to trust this as a primary source.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Trust level

Low

Usefulness score

5/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence 45%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research."

Benchmarks / Datasets

partial

BIRD

Useful for quick benchmark comparison.

"To address this, we developed a multi-round, expert-driven verification pipeline and used it to curate BIRD-Platinum, a dataset of 2.5k verified instances sampled from BIRD Train, with errors corrected in 61% of instances."

Reported Metrics

partial

Accuracy

Useful for evaluation criteria comparison.

"Recent efforts have focused on improving accuracy by building increasingly complex multi-stage large LLM pipelines, layering task decomposition, schema linking, and model-based query selection on top of an LLM."

Rater Population

partial

Domain Experts

Helpful for staffing comparability.

"Despite this growing complexity, a substantial gap (>10%) between such systems and human experts persists on benchmarks, suggesting that pipeline engineering alone has hit a ceiling."

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Domain Experts
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Low
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

BIRD

Reported Metrics

accuracy

Research Brief

Metadata summary

Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • Translating natural language questions to SQL queries (Text-to-SQL) is a long-standing problem in database research.
  • Recent efforts have focused on improving accuracy by building increasingly complex multi-stage large LLM pipelines, layering task decomposition, schema linking, and model-based query selection on top of an LLM.
  • Despite this growing complexity, a substantial gap (>10%) between such systems and human experts persists on benchmarks, suggesting that pipeline engineering alone has hit a ceiling.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Research Summary

Contribution Summary

  • However, despite these extensive architectural engineering efforts, a significant gap remains: even state-of-the-art (SOTA) AI agents have not yet achieved the human-level accuracy on the BIRD benchmark.
  • We introduce ReViSQL, a streamlined framework that achieves human-level accuracy on BIRD for the first time.
  • By training on BIRD-Verified, we show that improving data quality alone boosts the single-generation accuracy by 8.2-13.9% under the same RLVR algorithm.

Why It Matters For Eval

  • However, despite these extensive architectural engineering efforts, a significant gap remains: even state-of-the-art (SOTA) AI agents have not yet achieved the human-level accuracy on the BIRD benchmark.
  • We introduce ReViSQL, a streamlined framework that achieves human-level accuracy on BIRD for the first time.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: BIRD

  • Pass: Metric reporting is present

    Detected: accuracy

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.