# SEED: Domain-Specific Data Curation With Large Language Models

arXiv: https://arxiv.org/abs/2310.00749 · HTML: https://mlsanity.com/paper/2310.00749/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 75 references that are in the map.
- First posted on arXiv 1 Oct 2023.

## Builds on (most cited first, 27 of 27)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://mlsanity.com/paper/2108.13487/) (2021)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory](https://mlsanity.com/paper/2306.03901/) (2023)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers](https://mlsanity.com/paper/2106.11455/) (2021)
- [ReCode: Robustness Evaluation of Code Generation Models](https://mlsanity.com/paper/2212.10264/) (2022)
- [HoloClean: Holistic Data Repairs with Probabilistic Inference](https://mlsanity.com/paper/1702.00820/) (2017)
- [RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit](https://mlsanity.com/paper/2306.05212/) (2023)
- [DOM-LM: Learning Generalizable Representations for HTML Documents](https://mlsanity.com/paper/2201.10608/) (2022)
- [Supervised Contrastive Learning for Product Matching](https://mlsanity.com/paper/2202.02098/) (2022)
- [Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation](https://mlsanity.com/paper/2306.08891/) (2023)
- [Simplified DOM Trees for Transferable Attribute Extraction from the Web](https://mlsanity.com/paper/2101.02415/) (2021)

## Built on by (most cited first, 10 of 10)

- [Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap](https://mlsanity.com/paper/2401.10034/) (2024)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance](https://mlsanity.com/paper/2411.03562/) (2024)
- [A Survey on Large Language Model-based Agents for Statistics and Data Science](https://mlsanity.com/paper/2412.14222/) (2024)
- [GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis](https://mlsanity.com/paper/2507.21035/) (2025)
- [LLM-Enhanced Data Management](https://mlsanity.com/paper/2402.02643/) (2024)
- [Identify Critical Nodes in Complex Network with Large Language Models](https://mlsanity.com/paper/2403.03962/) (2024)
- [GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis](https://mlsanity.com/paper/2406.15341/) (2024)
- [FactFlow: Automatic Fact Sheet Generation and Customization from Tabular Dataset via AI Chain Design & Implementation](https://mlsanity.com/paper/2502.17909/) (2025)
- [Why can't Epidemiology be automated (yet)?](https://mlsanity.com/paper/2507.15617/) (2025)

## Abstract (arXiv)

Data curation tasks that prepare data for analytics are critical for turning data into actionable insights. However, due to the diverse requirements of applications in different domains, generic off-the-shelf tools are typically insufficient. As a result, data scientists often have to develop domain-specific solutions tailored to both the dataset and the task, e.g. writing domain-specific code or training machine learning models on a sufficient number of annotated examples. This process is notoriously difficult and time-consuming. We present SEED, an LLM-as-compiler approach that automatically generates domain-specific data curation solutions via Large Language Models (LLMs). Once the user describes a task, input data, and expected output, the SEED compiler produces a hybrid pipeline that combines LLM querying with more cost-effective alternatives, such as vector-based caching, LLM-generated code, and small models trained on LLM-annotated data. SEED features an optimizer that automatically selects from the four LLM-assisted modules and forms a hybrid execution pipeline that best fits the task at hand. To validate this new, revolutionary approach, we conducted experiments on 9 datasets spanning over 5 data curation tasks. In comparison to solutions that use the LLM on every data record, SEED achieves state-of-the-art or comparable few-shot performance, while significantly reducing the number of LLM calls.