🏷️ AutoDDG: Automated Dataset Description Generation using Large Language Models

Overview

This repository contains the official implementation for the SIGMOD 2026 paper:

AutoDDG: Automated Dataset Description Generation using Large Language Models

AutoDDG is an automated system for generating comprehensive, accurate, readable, and concise dataset descriptions. The framework combines a data-driven approach to summarize dataset contents with large language models (LLMs) to enrich summaries with semantic information and produce human-readable descriptions. AutoDDG supports both API-based (OpenAI) and local LLM (transformers) modes, providing flexibility for different deployment scenarios.

Installation

Clone the repository and install dependencies via uv (recommended):

git clone https://github.com/VIDA-NYU/AutoDDG.git
cd AutoDDG
uv sync
# If you do not have uv installed:
# * `curl -LsSf https://astral.sh/uv/install.sh | sh`
# * or look at https://docs.astral.sh/uv/getting-started/installation/

Then launch Jupyter Lab to explore:

uv run --with jupyter jupyter lab

Alternatively, install directly via pip:

pip install git+https://github.com/VIDA-NYU/AutoDDG@main

For local LLM support (Qwen, Llama, etc.), install with optional dependencies:

Using uv (recommended):

uv sync --extra local-llm

Using pip:

pip install git+https://github.com/VIDA-NYU/AutoDDG@main[local-llm]
# or
pip install git+https://github.com/VIDA-NYU/AutoDDG@main transformers torch

[!CAUTION] This installation method is temporary. A PyPI release of AutoDDG will soon be available. The git+https method will be deprecated in favor of the PyPI index.

---

Getting Started

AutoDDG supports both API-based (OpenAI) and local LLM (transformers) modes.

Using OpenAI API

The simplest way to use AutoDDG is with an OpenAI API client:

from openai import OpenAI
from autoddg import AutoDDG

# Setup OpenAI client
client = OpenAI(api_key="sk-...")

# Initialize AutoDDG
autoddg = AutoDDG(client=client, model_name="gpt-4o-mini")

# Generate description from a small CSV sample
sample_csv = """Case_ID,Age,BMI
C3L-00004,72,22.8
C3L-00010,30,34.15
"""

prompt, description = autoddg.describe_dataset(dataset_sample=sample_csv)

print(description)
# >>> This dataset contains medical information about patients, including their unique Case_ID, Age, and Body Mass Index (BMI). etc.

Using Local LLM

AutoDDG also supports local LLMs via transformers (Qwen, Llama, etc.):

from autoddg import AutoDDG

# Initialize AutoDDG with local LLM
autoddg = AutoDDG(
    client=None,
    model_name="Qwen/Qwen2.5-7B-Instruct",  # or any HuggingFace model
    use_local_llm=True,
    local_llm_device="cuda",  # or "cpu" if no GPU
    local_llm_dtype="bfloat16",  # or "float16", "float32"
)

# Generate description
sample_csv = """Case_ID,Age,BMI
C3L-00004,72,22.8
C3L-00010,30,34.15
"""

prompt, description = autoddg.describe_dataset(dataset_sample=sample_csv)
print(description)

Note: For local LLM support, ensure you have installed the optional dependencies:

pip install transformers torch

Semantic Profiler Processing Modes

AutoDDG provides multiple processing modes for semantic profiling to optimize performance based on your use case:

Mode	OpenAI API	Local LLM	Description
Sequential	✅	✅	Default mode, processes columns one by one
Multi-threading	✅	❌	Concurrent processing for faster execution
Group-prompting	✅	✅	Processes multiple columns in one prompt
Batch processing	❌	✅	Efficient GPU utilization for local models

Sequential Mode (Default)

The default mode processes columns sequentially. Works with both API and local LLMs:

# Sequential mode (default)
semantic_profile = autoddg.analyze_semantics(dataframe)

Multi-threading Mode (OpenAI API Only)

Use multi-threading to process columns concurrently for faster execution. Only available for OpenAI API clients:

# Multi-threading mode (OpenAI API only)
semantic_profile = autoddg.analyze_semantics(
    dataframe,
    use_multi_threading=True,
    max_workers=32,  # Optional: number of concurrent workers
)

Group-prompting Mode (Both API and Local LLM)

Process multiple columns in a single prompt to reduce API calls. Efficient for both API and local LLMs:

# Group-prompting: process all columns at once
semantic_profile = autoddg.analyze_semantics(
    dataframe,
    use_group_prompting=True,
    group_size=0,  # 0 = all columns at once, >0 = group size
)

# Or process in groups of 5 columns
semantic_profile = autoddg.analyze_semantics(
    dataframe,
    use_group_prompting=True,
    group_size=5,
)

Batch Processing Mode (Local LLM Only)

For local LLMs, use batch processing for efficient GPU utilization. Only available for local LLMs:

# Batch processing mode (Local LLM only)
semantic_profile = autoddg.analyze_semantics(
    dataframe,
    use_batch_processing=True,
    batch_size=32,  # Number of columns to process per batch
)

Important Notes:

• Multi-threading is only available for OpenAI API clients
• Batch processing is only available for local LLMs
• Group-prompting works with both API and local LLMs
• Batch processing takes precedence over other modes if enabled

Quick Jupyter Notebook Start

For a much better introduction, we highly recommend starting with the quick_start notebook with an example dataset.

---

How to Cite

If you use AutoDDG in your research, please cite our work:

@article{autoddg-sigmod2026,
Author = {Haoxiang Zhang and Yurong Liu and Wei-Lun Hung and Aécio Santos and Juliana Freire},
Title = {AutoDDG: Automated Dataset Description Generation using Large Language Models},
Journal = {Proceedings of the ACM on Management of Data},
volume = {4},
number = {1},
articleno = {12},
numpages = {27},
url = {https://doi.org/10.1145/3786626},
doi = {10.1145/3786626},
Year = {2026}
}

A preprint of the paper is available on arxiv: https://arxiv.org/abs/2502.01050

@misc{2502.01050,
Author = {Haoxiang Zhang and Yurong Liu and Wei-Lun Hung and Aécio Santos and Juliana Freire},
Title = {AutoDDG: Automated Dataset Description Generation using Large Language Models},
Year = {2025},
Eprint = {arXiv:2502.01050},
}

---

License

AutoDDG is released under the Apache License 2.0.