Saved in:
Bibliographic Details
Main Authors: Askari, Arian, Poelitz, Christian, Tang, Xinye
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.12692
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929642988896256
author Askari, Arian
Poelitz, Christian
Tang, Xinye
author_facet Askari, Arian
Poelitz, Christian
Tang, Xinye
contents Self-correction in text-to-SQL is the process of prompting large language model (LLM) to revise its previously incorrectly generated SQL, and commonly relies on manually crafted self-correction guidelines by human experts that are not only labor-intensive to produce but also limited by the human ability in identifying all potential error patterns in LLM responses. We introduce MAGIC, a novel multi-agent method that automates the creation of the self-correction guideline. MAGIC uses three specialized agents: a manager, a correction, and a feedback agent. These agents collaborate on the failures of an LLM-based method on the training set to iteratively generate and refine a self-correction guideline tailored to LLM mistakes, mirroring human processes but without human involvement. Our extensive experiments show that MAGIC's guideline outperforms expert human's created ones. We empirically find out that the guideline produced by MAGIC enhances the interpretability of the corrections made, providing insights in analyzing the reason behind the failures and successes of LLMs in self-correction. All agent interactions are publicly available at https://huggingface.co/datasets/microsoft/MAGIC.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12692
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL
Askari, Arian
Poelitz, Christian
Tang, Xinye
Computation and Language
Artificial Intelligence
Databases
Human-Computer Interaction
Self-correction in text-to-SQL is the process of prompting large language model (LLM) to revise its previously incorrectly generated SQL, and commonly relies on manually crafted self-correction guidelines by human experts that are not only labor-intensive to produce but also limited by the human ability in identifying all potential error patterns in LLM responses. We introduce MAGIC, a novel multi-agent method that automates the creation of the self-correction guideline. MAGIC uses three specialized agents: a manager, a correction, and a feedback agent. These agents collaborate on the failures of an LLM-based method on the training set to iteratively generate and refine a self-correction guideline tailored to LLM mistakes, mirroring human processes but without human involvement. Our extensive experiments show that MAGIC's guideline outperforms expert human's created ones. We empirically find out that the guideline produced by MAGIC enhances the interpretability of the corrections made, providing insights in analyzing the reason behind the failures and successes of LLMs in self-correction. All agent interactions are publicly available at https://huggingface.co/datasets/microsoft/MAGIC.
title MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL
topic Computation and Language
Artificial Intelligence
Databases
Human-Computer Interaction
url https://arxiv.org/abs/2406.12692