Integrating knowledge graphs and multilingual scholarly corpora for domain-adaptive LLMs in SSH

This paper presents an ongoing use case developed within the European project LLMs4EU and the ALT-EDIC infrastructure, aimed at adapting foundation models to Social Sciences and Humanities (SSH) research practices. The initiative supports tasks such as question answering, comparative document analysis, and literature review by integrating knowledge graphs and multilingual scholarly corpora.

The evaluation framework follows the LLMs4EU protocol and encompasses independent quantitative benchmarking for retrieval, summarization, traceability, and hallucination detection. It also includes a qualitative assessment involving a panel of Digital Humanities experts to ensure domain sensitivity.

By embedding model adaptation within research infrastructures and a structured legal and ethical compliance framework, the use case explores how domain-sensitive and regulation-aware generative AI can support SSH scholarship while preserving reliability and epistemic responsibility.