The submission investigates how large language models (LLMs) can support the formulation of complex queries in scientific information systems, using the Federated Content Search (FCS) and its LexCQL query language as an example. Access to such systems is often hindered by implicit technical knowledge requirements, limited usability, and linguistic barriers. LLMs offer a promising alternative by enabling intuitive, natural-language interaction.

A key challenge is the absence of natural-language, real-world user requests, as systems like the FCS operate exclusively with formal queries. To address this gap, synthetic information needs are generated by transforming existing query logs into natural-language user queries using LLMs, guided by simplified personas. These synthetic queries are then translated back into LexCQL, allowing both stages to be evaluated without a gold standard. Manual evaluation of 280 samples each shows that most generated information needs correctly reflect the underlying technical queries and most generated LexCQL queries are predominantly correct, confirming the feasibility of the approach.

The evaluation also reveals shortcomings in the underlying technical specification. These findings will be incorporated into the next revision of the specification and demonstrate how gaps in the clarity of technical documentation can be identified that are relevant both for humans and for its use in LLM-based applications.

Library collections are one of the main subjects of study in the digital humanities. Since their origin and the advent of the humanities computing, the application of formalised and automated processes to the humanities has been a response to needs that arose mainly in a linguistic and literary context.

If it is established that digital humanities (DH) and library and information science (LIS) share some of their research objects, albeit adopting different perspectives and methodologies, the aim of this paper is to demonstrate that the relationship between these two disciplinary fields does not only concern bibliographic and documentary heritage (and therefore libraries as institutions for conservation and sources of texts to be studied and from which, for example, digital editions can be obtained), but also involves the very nature of these disciplines. In both cases, in fact, there is a theoretical component and a technical and practical component, as well as an openness to comparison and interdisciplinarity (with other humanities disciplines, but not only). The aim of this paper is to identify similarities, including epistemological ones, between digital humanities and library and information science as a discipline.

This paper presents some of the results of a research project carried out in recent years by the author; the paper presented here focuses, in particular, on the research topics addressed in the main Italian scientific journals of digital humanities and library and information science to highlight the current points of contact and relationships between digital humanities and library and information science in Italy and what future developments may be.

Generative artificial intelligence is rapidly entering the humanities, yet its integration into established research infrastructures remains insufficiently examined. This paper presents a case study on embedding large language models (LLMs) into lexicographic workflows for semantic classification. The project implements an AI-supported system for assigning lexical meanings to a controlled semantic framework used in German dialect lexicography. In a controlled evaluation of 1,000 meanings, model-generated suggestions achieved an adoption rate of over 90%, including additional proposals judged equally valid by experienced editors of approximately 10%. On this basis, a web service was developed and integrated into the editorial environments of three dialect dictionary projects.

The paper moves beyond performance metrics to analyze what happens when generative AI (GenAI) becomes part of an operational humanities infrastructure by evaluating the LLM-based process in a ongoing study that will be finalized in summer. Within a hybrid human-AI workflow, the system generates up to three classification suggestions per entry, while editorial authority remains fully intact. The integration has measurably reduced search effort, stabilized decision-making, and enabled the scalable structuring of large legacy datasets comprising more than 40,000 meanings.

At the same time, the study addresses the epistemic consequences of algorithmic assistance. When model suggestions function as recurring reference points, subtle standardization effects and forms of emerging algorithmic authority may arise. A structured user study evaluating acceptance, efficiency gains, and perceived risks is currently underway, with full results to be presented at the conference. The findings suggest that sustainable AI integration in the Digital Humanities depends not on automation alone, but on carefully designed hybrid systems that combine efficiency gains with transparent governance and continuous critical oversight.