LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

• URL: http://arxiv.org/abs/2504.02327v1
• Date: Thu, 03 Apr 2025 06:59:44 GMT
• Title: LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models
• Authors: Weibin Liao, Xin Gao, Tianyu Jia, Rihong Qiu, Yifan Zhu, Yang Lin, Xu Chu, Junfeng Zhao, Yasha Wang,
• Abstract summary: We propose a novel framework that improves the performance of open-source Large Language Models (LLMs) on complex NL2 tasks through task decomposition and reinforcement learning.<n>LearNAT enables an open-source LLM to achieve performance comparable to GPT-4, while offering improved efficiency and accessibility.
• Score: 28.17495423015754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Natural Language to SQL (NL2SQL) has emerged as a critical task for enabling seamless interaction with databases. Recent advancements in Large Language Models (LLMs) have demonstrated remarkable performance in this domain. However, existing NL2SQL methods predominantly rely on closed-source LLMs leveraging prompt engineering, while open-source models typically require fine-tuning to acquire domain-specific knowledge. Despite these efforts, open-source LLMs struggle with complex NL2SQL tasks due to the indirect expression of user query objectives and the semantic gap between user queries and database schemas. Inspired by the application of reinforcement learning in mathematical problem-solving to encourage step-by-step reasoning in LLMs, we propose LearNAT (Learning NL2SQL with AST-guided Task Decomposition), a novel framework that improves the performance of open-source LLMs on complex NL2SQL tasks through task decomposition and reinforcement learning. LearNAT introduces three key components: (1) a Decomposition Synthesis Procedure that leverages Abstract Syntax Trees (ASTs) to guide efficient search and pruning strategies for task decomposition, (2) Margin-aware Reinforcement Learning, which employs fine-grained step-level optimization via DPO with AST margins, and (3) Adaptive Demonstration Reasoning, a mechanism for dynamically selecting relevant examples to enhance decomposition capabilities. Extensive experiments on two benchmark datasets, Spider and BIRD, demonstrate that LearNAT enables a 7B-parameter open-source LLM to achieve performance comparable to GPT-4, while offering improved efficiency and accessibility.

Related papers

• New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration [49.180693704510006]
  Referring Expression (REC) is a cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding.<n>We introduce a new REC dataset with two key features. First, it is designed with controllable difficulty levels, requiring fine-grained reasoning across object categories, attributes, and relationships.<n>Second, it incorporates negative text and images generated through fine-grained editing, explicitly testing a model's ability to reject non-existent targets.
  arXiv  Detail & Related papers  (2025-02-27T13:58:44Z)
• ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL [42.019659095480726]
  We propose a novel RObust mUltitask Tuning and collaboration mEthod (ROUTE) to improve the comprehensive capabilities of open-source LLMs for Text2. Our approach begins with multi-task supervised fine-tuning (SFT) using various synthetic training data related tosql generation. We also introduce a Multitask Collaboration Prompting (MCP) strategy to reduce hallucinations duringsql generation.
  arXiv  Detail & Related papers  (2024-12-13T13:41:18Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• DeTriever: Decoder-representation-based Retriever for Improving NL2SQL In-Context Learning [19.93800175353809]
  DeTriever is a novel demonstration retrieval framework that learns a weighted combination of hidden states. Our method significantly outperforms the state-of-the-art baselines on one-shot NL2 tasks.
  arXiv  Detail & Related papers  (2024-06-12T06:33:54Z)
• CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language Model [1.9950682531209156]
  Domain-Specific Chinese Relation Extraction (DSCRE) aims to extract relations between entities from domain-specific Chinese text. Given the impressive performance of large language models (LLMs) in natural language processing, we propose a new framework called CRE-LLM.
  arXiv  Detail & Related papers  (2024-04-28T06:27:15Z)
• PURPLE: Making a Large Language Model a Better SQL Writer [14.627323505405327]
  We propose PURPLE, which improves accuracy by retrieving demonstrations containing the requisite logical operator composition for the NL2 task. PURPLE achieves a new state-of-the-art performance of 80.5% exact-set match accuracy and 87.8% execution match accuracy on the validation set of the popular NL2 benchmark.
  arXiv  Detail & Related papers  (2024-03-29T07:01:29Z)
• Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm [19.06214756792692]
  In-context learning of large-language models (LLMs) has achieved remarkable success in the field of natural language processing. Case studies reveal that the single-step chain-of-thought approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-correction. A workflow paradigm is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition.
  arXiv  Detail & Related papers  (2024-02-16T13:24:05Z)
• kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning [50.40636157214161]
  Task-Oriented Parsing (TOP) enables conversational assistants to interpret user commands expressed in natural language. LLMs have achieved impressive performance in computer programs based on a natural language prompt. This paper focuses on harnessing the capabilities of LLMs for semantic parsing tasks.
  arXiv  Detail & Related papers  (2023-12-17T17:26:50Z)
• ADaPT: As-Needed Decomposition and Planning with Language Models [131.063805299796]
  We introduce As-Needed Decomposition and Planning for complex Tasks (ADaPT) ADaPT explicitly plans and decomposes complex sub-tasks as-needed, when the Large Language Models is unable to execute them. Our results demonstrate that ADaPT substantially outperforms established strong baselines.
  arXiv  Detail & Related papers  (2023-11-08T17:59:15Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [76.76046657162306]
  Large language models (LLMs) have emerged as a new paradigm for Text-to- task. Large language models (LLMs) have emerged as a new paradigm for Text-to- task.
  arXiv  Detail & Related papers  (2023-08-29T14:59:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.