Metraipolis › archive › dc_c49803bf356e

chATLAS: A Retrieval-Augmented Conversational Assistant for the ATLAS Experiment — arXiv:2610.37697

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37697
License (as archived)
CC0-1.0
Archived
2026-11-01T02:39:55.508Z
SHA-256 of the archived text
d8c9e11ff9881d31f12e0bdcb6f30fa815883b3e5a90387d24c10e64fb4ba1c2
Stable URL of this page
https://metraipolis.com/documento/dc_c49803bf356e

How to cite

chATLAS: A Retrieval-Augmented Conversational Assistant for the ATLAS Experiment — arXiv:2610.37697 — arXiv (en), https://arxiv.org/abs/2610.37697 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c49803bf356e (Metraipolis archive dc_c49803bf356e, sha256 d8c9e11ff9881d31f12e0bdcb6f30fa815883b3e5a90387d24c10e64fb4ba1c2)
BibTeX
@misc{dcc49803bf356e,
  title = {chATLAS: A Retrieval-Augmented Conversational Assistant for the ATLAS Experiment — arXiv:2610.37697},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37697},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c49803bf356e; sha256 d8c9e11ff9881d31f12e0bdcb6f30fa815883b3e5a90387d24c10e64fb4ba1c2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37697. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large scientific collaborations produce extensive internal documentation spread across heterogeneous systems, making it difficult for collaborators to locate and reuse existing knowledge. We present chATLAS, a deployed Retrieval-Augmented Generation (RAG) assistant developed for the ATLAS experiment at CERN. The system provides conversational access to more than 30,000 documents from several collaboration resources, material largely unavailable to general-purpose language models, using hybrid dense--sparse retrieval deployed on CERN infrastructure. A domain-specific benchmark built from automatically generated question--answer pairs is used to evaluate retrieval and generation performance and to guide design choices. We study the selection and domain-specific fine-tuning of an embedding model, contextual retrieval, ranking strategies, and generator choice. Fine-tuning combined with contextual retrieval more than doubles how often the correct document is returned as the top result on the most technically challenging documentation source. The deployed system also includes intent routing, safety handling, Mattermost integration, and an MCP server for future agentic workflows. chATLAS demonstrates that domain-adapted RAG can provide source-attributed, domain-specific access to collaboration knowledge, and offers a practical foundation for scientific collaborations and other organisations that rely on accurate, up-to-date retrieval from proprietary documentation.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; High Energy Physics - Experiment (hep-ex).
Pagina del lavoro: https://arxiv.org/abs/2610.37697 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:16:28.215Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).