EVE: A Domain-Specific LLM Framework for Earth Intelligence
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...
| Authors | Àlex R. Atrio, Antonio Lopez, Jino Rohit et al. |
|---|---|
| Primary category | cs.CL |
| Published | 20 March 2026 |
| Last updated at source | 25 April 2026 |
Connected in the knowledge graph
- eve-esa/corpusDataset · cited by
- eve-esa/mcqa-multiple-answersDataset · cited by
- eve-esa/open-ended-w-contextDataset · cited by
- eve-esa/mcqa-single-answerDataset · cited by
- eve-esa/hallucination-detectionDataset · cited by
- eve-esa/synthDataset · cited by
Models and datasets referencing this paper
- eve-esa/synthDataset
- eve-esa/corpusDataset
- eve-esa/mcqa-single-answerDataset
- eve-esa/mcqa-multiple-answersDataset
- eve-esa/hallucination-detectionDataset
- eve-esa/open-ended-w-contextDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.