# DPC: A Training-Free Dual-Paradigm Consistency Framework for Text-to-SQL Candidate Selection

> DPC achieves SQL candidate selection without training by constructing a Minimal Distinction Database and cross-paradigm validation, with an accuracy improvement of up to 2.2%.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-04-16T15:44:13.000Z
- 最近活动: 2026-04-17T03:22:16.635Z
- 热度: 135.4
- 关键词: Text-to-SQL, 候选选择, 多智能体, 跨范式验证, LLM评估, 代码生成
- 页面链接: https://www.zingnex.cn/en/forum/thread/dpc-text-to-sql
- Canonical: https://www.zingnex.cn/forum/thread/dpc-text-to-sql
- Markdown 来源: floors_fallback

---

## DPC: A Training-Free Dual-Paradigm Consistency Framework for Text-to-SQL Candidate Selection (Introduction)

DPC (Dual-Paradigm Consistency) is a training-free Text-to-SQL candidate selection framework that corely addresses the "generation-selection gap" problem of LLMs in Text-to-SQL tasks. It achieves an accuracy improvement of up to 2.2% by constructing a Minimal Distinction Database (MDD) and a cross-paradigm validation strategy. This thread will introduce its background, methods, experimental results, and application prospects in separate floors.

## The Generation-Selection Gap in Text-to-SQL and Dilemmas of Existing Solutions (Background)

### The Generation-Selection Gap in Text-to-SQL
Although LLMs can generate SQL, they lack self-evaluation ability without an execution environment, leading to high Pass@K but low Pass@1 (only one can be selected in practical applications), forming the "generation-selection gap."

### Dilemmas of Existing Solutions
- **Supervised Verifiers**: Require large amounts of labeled data, prone to overfitting, and have poor generalization;
- **Self-Consistency**: If the model has systematic biases, it is prone to "consensus hallucination";
- **LLM-as-a-Judge**: Lack symbolic execution ability and are easily misled by surface features.

## Core Ideas of DPC and Multi-Agent Collaboration Architecture (Methods)

The core idea of DPC is to transform SQL selection from probabilistic guessing into deterministic verification with visible data. It adopts a three-agent collaboration architecture:
- **SLICER**: Analyzes the structure of SQL candidates and identifies key differences;
- **TESTER**: Constructs a Minimal Distinction Database (MDD) based on the differences;
- **SOLVER**: Performs cross-paradigm validation (converts SQL to Python/Pandas) and compares the consistency of execution results.

## Innovative Design of Minimal Distinction Database and Cross-Paradigm Validation (Method Details)

### Minimal Distinction Database (MDD)
MDD is a key innovation of DPC, with the following features:
- Adversarial design: Constructed in a targeted manner to maximize candidate differences;
- Fully observable: Data is visible and controllable, with transparent verification;
- Minimal scale: Contains only the minimum data needed for distinction, reducing costs;
- Logic-focused: Precisely exposes differences in boundary conditions, null value handling, etc.

### Cross-Paradigm Validation
Implemented by converting SQL to Python/Pandas:
- Paradigm independence: Declarative (SQL) and imperative (Python) syntax have different thinking patterns; if results are consistent, the credibility is high;
- Bias offset: Different paradigms are less likely to have the same systematic biases;
- Executable verification: Pandas provides a reliable execution foundation.

## Experimental Verification and Performance (Evidence)

### Experimental Results
Evaluated on mainstream LLMs using BIRD and Spider benchmarks:
- Accuracy improvement: 2.2% higher than baselines like Self-Consistency;
- Consistency advantage: Stable across different models and query difficulties;
- Training-agnostic: No training required, with strong generality.

### Ablation Experiments
- Necessity of MDD: Replacing MDD with random data leads to a significant performance drop;
- Value of cross-paradigm: Single-paradigm verification has low accuracy;
- Multi-agent collaboration: Individual agents cannot achieve the performance of the complete system.

## Technical Insights and Application Prospects (Conclusions and Recommendations)

### Technical Insights
- From guessing to verification: Constructing a controllable test environment is more reliable than relying on probabilistic outputs;
- Cross-paradigm redundancy: Cross-validation reduces the risk of systematic biases;
- Agent specialization: Decomposing tasks to specialized agents improves performance;
- Interpretability: The verification process is transparent, and decision reasons can be traced.

### Application Prospects
- Code generation: Can be extended to other executable code scenarios;
- Formal verification: Explore high-reliability fields by combining with symbolic execution;
- Multi-agent systems: The collaboration architecture can be extended to more AI scenarios.

## Limitations and Future Outlook (Supplementary)

### Limitations
- MDD construction has computational overhead; complex queries may lead to state space explosion;
- Cross-paradigm validation requires a reliable execution environment for the target language.

### Conclusion
DPC provides a new idea for solving the Text-to-SQL generation-selection gap, and its method combining MDD and cross-paradigm validation is of great significance in building reliable intelligent systems.