Work Stanford University

The first LLM extraction model for oil-industry research papers — built before GPT went public.

Text-extraction LLM
Stanford Doerr School of Sustainability View research project
The challenge

Stanford’s Oil Production Greenhouse Gas Emissions Estimator (OPGEE) team needed to extract structured data from decades of technical papers in the Oil & Gas sector, each taking researchers 4–5 hours to process manually. With over 30,000 papers in backlog, completing the task by hand would have required 40+ years of manual effort.

Our approach

57Blocks developed the first domain-specific LLM extraction model for the oil industry, trained before GPT’s public release. Using an ensemble approach, domain-tuned LLMs, and prompt-engineering pipelines, the system automatically extracted and normalized emissions-related data from unstructured academic and industry papers.

The results
Extraction time
< 10 min
Per paper, down from 4–5 hours of manual work.
Accuracy
~96%
Across diverse academic and industry publication sources.
Cost
< $1
Per paper extracted, at production scale.
Throughput
30,000+
Backlogged papers made processable through scalable pipelines.
Business impact

Enabled OPGEE researchers to process tens of thousands of legacy papers efficiently, unlocking decades of emissions data and accelerating climate-impact modeling for the global energy sector.

Further reading
Read the publication in ScienceDirect OPGEE research project at Stanford

This research was funded by the Aramco Services Company and Natural Gas Initiatives at Stanford University. We thank the Microsoft Accelerate Foundation Models Research Program and Kenji Takeda for providing Azure OpenAI services and credits. We appreciate 57Blocks and Lastmile.ai for their GitHub and cloud computing infrastructure support. Thanks to Jill Marie O’Nan for writing suggestions, and to Thuy Nguyen and Cerise Burns for managing administrative tasks.

Let's build with you.

Tell us what you are working on.

Talk to our team See our work