Meta-aware Learning in text-to-SQL Large Language Model
The advancements of Large language models (LLMs) have provided great opportunities to text-to-SQL tasks to overcome the main challenges to understand complex domain information and complex database structures in business applications. In this paper, we propose a meta-aware learning framework to integrate domain knowledge, database schema, chain-of-thought reasoning processes, and metadata relationships to improve the SQL generation quality. The proposed framework includes four learning strategies: schema-based learning, Chain-of-Thought (CoT) learning, knowledge-enhanced learning, and key information tokenization. This approach provides a comprehensive understanding of database structure and metadata information towards LLM through fine-tuning to improve its performance on SQL generation within business domains. Through two experimental studies, we have demonstrated the superiority of the proposed methods in execution accuracy, multi-task SQL generation capability, and reduction of catastrophic forgetting.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelText to SQLText-To-SQLSimilar Papers 제목 키워드 기반
Context-Aware Meta-Learning
Large Language Models like ChatGPT demonstrate a remarkable capacity to learn new concepts during inference without any fine-tuning. However, visual models trained to detect new objects during inference have been unable …
Few-Shot Image ClassificationIn-Context LearningMeta-Learninguniversal meta-learningUtilizing Metadata for Better Retrieval-Augmented Generation
Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory …
LaiDA: Linguistics-aware In-context Learning with Data Augmentation for Metaphor Components Identification
Metaphor Components Identification (MCI) contributes to enhancing machine understanding of metaphors, thereby advancing downstream natural language processing tasks. However, the complexity, diversity, and dependency on …
Data AugmentationDiversityGraph AttentionIn-Context LearningSearching Meta Reasoning Skeleton to Guide LLM Reasoning
Meta reasoning behaviors work as a skeleton to guide large language model (LLM) reasoning, thus help to improve reasoning performance. However, prior researches implement meta reasoning skeleton with manually designed st…
MATCH: Metadata-Aware Text Classification in A Large Hierarchy
Multi-label text classification refers to the problem of assigning each given document its most relevant labels from the label set. Commonly, the metadata of the given documents and the hierarchy of the labels are availa…
ClassificationGeneral ClassificationMulti Label Text ClassificationMulti-Label Text Classification+2