EVE: A Domain-Specific LLM Framework for Earth Intelligence

Àlex R. Atrio, Antonio Lopez, Jino Rohit, Yassine El Ouahidi, Marcello Politi, Vijayasri Iyer, Umar Jamil, Sébastien Bratières, Nicolas Longépé

Keywords: Domain-Specific Language Model, LLM, Earth Intelligence, Retrieval-Augmented Generation, Hallucination

TL;DR: Earth Virtual Expert is an Earth Intelligence system centered on a domain-specialized LLM that outperforms comparable models. We release training and benchmarking data, and integrate retrieval and hallucination detection into a deployed system.

Abstract:

We introduce Earth Virtual Expert (EVE), the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Intelligence. At its core is EVE-Instruct, a domain-adapted 24B model built on Mistral Small 3.2 and optimized for reasoning and question answering. On newly constructed Earth Observation and Earth Sciences benchmarks, it outperforms comparable models while preserving general capabilities.
We release curated training corpora and the first systematic domain-specific evaluation benchmarks, covering MCQA, open-ended QA, and factuality. EVE further integrates RAG and a hallucination-detection pipeline into a production system deployed via API and GUI, supporting 350 pilot users. All models, datasets, and code are publicly available.

Submission Type: Deployed

Submission Number: 239