Self-Correction Distillation for Structured Data Question Answering
Yushan Zhu, Wen Zhang, Long Jin, Mengshu Sun, Ling Zhong, Zhiqiang Liu, Juan Li, Lei Liang
Abstract
Structured data question answering (QA), including table QA, Knowledge Graph (KG) QA, and temporal KG QA, is a pivotal research area. Advances in large language models (LLMs) have driven significant progress in unified structural QA frameworks like TrustUQA. However, these frameworks face challenges when applied to small-scale LLMs since small-scale LLMs are prone to errors in generating structured queries. To improve the structured data QA ability of small-scale LLMs, we propose a self-correction distillation (SCD) method. In SCD, an error prompt mechanism (EPM) is designed to detect errors and provide customized error messages during inference, and a two-stage distillation strategy is designed to transfer large-scale LLMs
BibTeX
@inproceedings{aaai2026_selfcorrectiondi,
title = {Self-Correction Distillation for Structured Data Question Answering},
author = {Yushan Zhu and Wen Zhang and Long Jin and Mengshu Sun and Ling Zhong and Zhiqiang Liu and Juan Li and Lei Liang and Chong Long and Chao Deng and Junlan Feng},
booktitle = {AAAI 2026},
year = {2026}
}