Artificial intelligence

Aware of these challenges, Cairn.info has been collaborating for several years with trusted partners specializing in automatic text and image processing (notably Pythagoria, Kairntech and Isako). The development of neural networks and the emergence of transformer models have enhanced the potential applications of the algorithmic solutions already in use on our portals thanks to these partnerships.

In terms of services, we mainly employ artificial intelligence for:

• metadata extraction: structuring bibliographic references and author affiliations, extracting keywords and named entities
• classification: grouping publications by semantic proximity, assigning to categories by discipline, and partitioning illustrations by type

In addition, we began experimenting with generative AI in 2024, focusing on:

• generating alternative texts for images, to further enhance publication accessibility
• developing a sourced question/answer model (RAG; Retrieval Augmented Generation)

These projects are carried out in compliance with the guidelines that Cairn.info has established for its use of artificial intelligence, pledging to:

• refrain from transmitting partner content to LLMs operated by major AI players;
• protect partner content from a technological (Datadome) and legal (TDMRep) standpoint;
• use generative AI to facilitate access to the academic corpus and not as an alternative to reading the original texts;
• involve partners (authors, publishers, librarians) in the implementation of AI projects in a transparent and collaborative manner; and
• prioritize digital sobriety by selecting the smallest language model capable of solving each problem.