---
title: "Self-Refining Prompt Induction for Streaming Text-to-SQL"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.00960v1"
permalink: "https://feed.astralor.com/items/itm_0b8f7edd0f18e4d41ecc838d"
published: "2026-10-31T14:02:40.000Z"
score: 55
channel: "tech"
tags: ["LLM","推理效率","RAG","Self-Refining Prompt Induction","Streaming Text-to-SQL Text-to-SQL","Text-to-SQL","SRPI","Refiner"]
---

# Self-Refining Prompt Induction for Streaming Text-to-SQL

## At a glance

Text-to-SQL assistants for streaming engines must handle dialect-specific types, windowing rules, and temporal semantics, including constructs poorly handled by generic prompts. We present Self-Refining Prompt Induction…

## Key points

- Text-to-SQL assistants for streaming engines must handle dialect-specific types, windowing rules, and temporal semantics, including constructs poorly handled by generic prompts.
- We present Self-Refining Prompt Induction (SRPI), an offline method that converts generation failures into reusable dialect instructions while keeping model weights fixed.
- A Refiner revises the Generator's prompt using reference-conditioned feedback from three LLM judges; a sampled regression guard checks earlier successes, and a separate Compressor reduces prompt length.

## Full text

Text-to-SQL assistants for streaming engines must handle dialect-specific types, windowing rules, and temporal semantics, including constructs poorly handled by generic prompts. We present Self-Refining Prompt Induction (SRPI), an offline method that converts generation failures into reusable dialect instructions while keeping model weights fixed. A Refiner revises the Generator's prompt using reference-conditioned feedback from three LLM judges; a sampled regression guard checks earlier successes, and a separate Compressor reduces prompt length. Inference uses the frozen prompt without retrieval or query repair. We evaluate cross-domain and cross-model transfer on Confluent Cloud Flink SQL using a controlled synthetic workload seeded by 30 expert-written examples, with 335 induction examples and 257 questions from held-out domains. The same induced prompt improves mean judge scores across seven Generators by 7.1-19.2 percentage points, including an increase from 85.3% to 97.5% for the induction model. A separate compression study reduces prompt length by 52.7% with a 0.19-percentage-point score decrease. An assistant using the induced prompt is in early access, with initial user feedback to inform subsequent refinement.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_0b8f7edd0f18e4d41ecc838d