arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.13071cs.CLcs.AI
收藏

EVE:面向地球智能的领域专用LLM框架

EVE: A Domain-Specific LLM Framework for Earth Intelligence

Pi School(Pi学校);Mistral AI;Translated;ESA Φ \Phi -lab(ESA Φ实验室)

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

AI总结:

EVE首次提出开源端到端框架,构建24B领域适应模型,在地球观测和科学基准上超越同类模型,提供系统化评估基准和生产系统,支持350名试点用户。

摘要:

我们介绍了地球虚拟专家(EVE),首个开源端到端项目,用于开发和部署专门用于地球智能的领域专用LLM。其核心是EVE-Instruct,基于Mistral Small 3.2构建的24B模型,优化了推理和问答能力。在新构建的地球观测和地球科学基准上,它在超越同类模型的同时保持通用能力。我们发布了精心挑选的训练语料库和首个系统化的领域特定评估基准,涵盖多项选择题、开放式问答和事实性。EVE进一步将RAG和幻觉检测流水线整合到通过API和GUI部署的生产系统中,目前已支持350名试点用户。所有模型、数据集和代码均已准备好在huggingface.co/eve-esa和github.com/eve-esa上以开放许可证发布。

英文摘要:

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 so far. All models, datasets, and code are ready to be released under open licenses as contributions to our field at huggingface.co/eve-esa and github.com/eve-esa.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑