UniDM: A Unified Framework for Data Manipulation with Large Language Models

TL;DR

UniDM introduces a unified, automatic framework leveraging large language models to perform diverse data manipulation tasks in data lakes, reducing manual effort and improving performance across multiple benchmarks.

Contribution

This paper presents UniDM, the first general framework that formalizes data manipulation tasks and employs LLMs with automatic context retrieval and prompting for broad applicability.

Findings

Achieves state-of-the-art results on various data manipulation benchmarks

Demonstrates high generality across multiple data tasks

Reduces manual effort in data lake management

Abstract

Designing effective data manipulation methods is a long standing problem in data lakes. Traditional methods, which rely on rules or machine learning models, require extensive human efforts on training data collection and tuning models. Recent methods apply Large Language Models (LLMs) to resolve multiple data manipulation tasks. They exhibit bright benefits in terms of performance but still require customized designs to fit each specific task. This is very costly and can not catch up with the requirements of big data lake platforms. In this paper, inspired by the cross-task generality of LLMs on NLP tasks, we pave the first step to design an automatic and general solution to tackle with data manipulation tasks. We propose UniDM, a unified framework which establishes a new paradigm to process data manipulation tasks using LLMs. UniDM formalizes a number of data manipulation tasks in a unified form and abstracts three main general steps to solve each task. We develop an automatic context retrieval to allow the LLMs to retrieve data from data lakes, potentially containing evidence and factual information. For each step, we design effective prompts to guide LLMs to produce high quality results. By our comprehensive evaluation on a variety of benchmarks, our UniDM exhibits great generality and state-of-the-art performance on a wide variety of data manipulation tasks.