GeoGPT-RAG Technical Report
Not on the map. Why?
Abstract (arXiv)
GeoGPT is an open large language model system built to advance research in the geosciences. To enhance its domain-specific capabilities, we integrated Retrieval Augmented Generation(RAG), which augments model outputs with relevant information retrieved from an external knowledge source. GeoGPT uses RAG to draw from the GeoGPT Library, a specialized corpus curated for geoscientific content, enabling it to generate accurate, context-specific answers. Users can also create personalized knowledge bases by uploading their own publication lists, allowing GeoGPT to retrieve and respond using user-provided materials. To further improve retrieval quality and domain alignment, we fine-tuned both the embedding model and a ranking model that scores retrieved passages by relevance to the query. These enhancements optimize RAG for geoscience applications and significantly improve the system's ability to deliver precise and trustworthy outputs. GeoGPT reflects a strong commitment to open science through its emphasis on collaboration, transparency, and community driven development. As part of this commitment, we have open-sourced two core RAG components-GeoEmbedding and GeoReranker-to support geoscientists, researchers, and professionals worldwide with powerful, accessible AI tools.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 18 Aug 2025.
Builds on
18 of 25 references.
References · 18
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
- 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
- 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
- 2020Fact or Fiction: Verifying Scientific Claimscited by 546
- 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 426
- 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
- 2023Improving Text Embeddings with Large Language Modelscited by 295
- 2019PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identificationcited by 262
- 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
- 2021ContractNLI: A Dataset for Document-level Natural Language Inference for Contractscited by 145
6 more
- 2017DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applicationscited by 110
- 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 81
- 2024Making Text Embedders Few-Shot Learnerscited by 78
- 2023T2Ranking: A large-scale Chinese Benchmark for Passage Rankingcited by 59
- 2024Injecting New Knowledge into Large Language Models via Supervised Fine-Tuningcited by 56
- 2022SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrievalcited by 21
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025RAG for Geoscience: What We Expect, Gaps and Opportunities
- 2023GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT
- 2024The Chronicles of RAG: The Retriever, the Chunk and the Generator
- 2024An LLM Agent for Automatic Geospatial Data Analysis
- 2025Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation
- 2024XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation
- 2024R^3AG: First Workshop on Refined and Reliable Retrieval Augmented Generation
- 2025OmniBench-RAG: A Multi-Domain Evaluation Platform for Retrieval-Augmented Generation Tools