paper-with-me

Papers

Fine-Tuning Language Models for Context-Specific SQL Query Generation

2023-12-04 · Amine Rebei

The ability to generate SQL queries from natural language has significant implications for making data accessible to non-specialists. This paper presents a novel approach to fine-tuning open-source large language models (LLMs) for the task of transforming natural language into SQL queries within the retail domain. We introduce models specialized in generating SQL queries, trained on synthetic datasets tailored to the Snowflake SQL and GoogleSQL dialects. Our methodology involves generating a context-specific dataset using GPT-4, then fine-tuning three open-source LLMs(Starcoder Plus, Code-Llama, and Mistral) employing the LoRa technique to optimize for resource constraints. The fine-tuned models demonstrate superior performance in zero-shot settings compared to the baseline GPT-4, with Code-Llama achieving the highest accuracy rates, at 81.58% for Snowflake SQL and 82.66% for GoogleSQL. These results underscore the effectiveness of fine-tuning LLMs on domain-specific tasks and suggest a promising direction for enhancing the accessibility of relational databases through natural language interfaces.

📄 PDF Abstract BibTeX arXiv:2312.02251

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Q-PEFT: Query-dependent Parameter Efficient Fine-tuning for Text Reranking with Large Language Models

2024-04-06 · Zhiyuan Peng, Xuyang Wu, Qifan Wang, Sravanthi Rajanala 외

Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs. Recent studies have shown h…

parameter-efficient fine-tuningRerankingText Reranking

DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation

2026-05-15 · Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le, Duy Cao Hoang 외 arxiv

Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from training corpora, they may produce hallucinat…

Prompt Engineering

HyQE: Ranking Contexts with Hypothetical Query Embeddings

2024-10-20 · Weichao Zhou, Jiaxin Zhang, Hilaf Hasson, Anu Singh 외

In retrieval-augmented systems, context ranking techniques are commonly employed to reorder the retrieved contexts based on their relevance to a user query. A standard approach is to measure this relevance through the si…

Retrieval

Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models

2024-03-25 · Atsushi Keyaki, Ribeka Keyaki

Fine-tuning in information retrieval systems using pre-trained language models (PLM-based IR) requires learning query representations and query-document relations, in addition to downstream task-specific learning. This s…

Information RetrievalRetrieval

FIRESPARQL: A LLM-based Framework for SPARQL Query Generation over Scholarly Knowledge Graphs

2025-08-14 · Xueli Pan, Victor de Boer, Jacco van Ossenbruggen arxiv

Question answering over Scholarly Knowledge Graphs (SKGs) remains a challenging task due to the complexity of scholarly content and the intricate structure of these graphs. Large Language Model (LLM) approaches could be …

Question AnsweringKnowledge Graphs