PulseAugur
LIVE 01:47:40
research · [1 source] ·
0
research

EVE framework launches open-source LLMs for Earth Intelligence

Researchers have developed EVE, an open-source framework for creating specialized Large Language Models (LLMs) focused on Earth Intelligence. The core of EVE is EVE-Instruct, a 24 billion parameter model derived from Mistral Small 3.2, which excels at reasoning and answering questions related to Earth Observation and Earth Sciences. This new model demonstrates superior performance on custom benchmarks while retaining general capabilities, and the project also releases curated training data and evaluation benchmarks. EVE includes a production system with Retrieval-Augmented Generation (RAG) and hallucination detection, supporting over 350 pilot users. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Provides a specialized LLM framework and open-source resources for Earth science applications, potentially accelerating research and development in the field.

RANK_REASON This is a research paper detailing the creation and release of a domain-specific LLM framework and model.

Read on arXiv cs.CL →

COVERAGE [1]

  1. arXiv cs.CL TIER_1 · \"Alex R. Atrio, Antonio Lopez, Jino Rohit, Yassine El Ouahidi, Marcello Politi, Vijayasri Iyer, Umar Jamil, S\'ebastien Brati\"eres, Nicolas Long\'ep\'e ·

    EVE: A Domain-Specific LLM Framework for Earth Intelligence

    arXiv:2604.13071v2 Announce Type: replace 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 …