EVE是首个面向地球科学的开源大模型框架，支持从训练到部署的全流程。
EVE: A Domain-Specific LLM Framework for Earth Intelligence
- 基于Mistral Small 3.2构建240亿参数专用模型，优化推理与问答能力。
- 在新构建的地球观测与科学评测中表现优于同类模型，且保持通用能力。
- 提供检索增强与幻觉检测系统，已服务350名试点用户，代码数据开源。
我们提出地球虚拟专家（EVE），首个面向地球智能领域的开源端到端大模型开发与部署框架。核心为EVE-Instruct，一个基于Mistral Small 3.2、经领域适配的240亿参数模型，专为推理与问答优化。在新构建的地球观测与地球科学评测集上，其性能超越同类模型，同时保留通用能力。研究团队发布了精选训练语料库及首个系统性的领域专用评估基准，涵盖多选题、开放式问答和事实性测试。EVE集成检索增强生成（RAG）与幻觉检测流水线，通过API与图形界面部署，目前已支持350名试点用户。所有模型、数据集与代码将按开源许可发布于huggingface.co/eve-esa与github.com/eve-esa。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。