LinkAhead is an open source research data management platform whose core functionality rests on a powerful semantic search engine. The engine exposes a purpose-built query language called CQL that resembles English, enabling both interactive exploration through a graphical user interface and programmatic access in automated workflows. Despite its intuitive design, mastering the query syntax, particularly for complex, multi-hop traversals of LinkAhead’s graph-structured metadata (e.g., reference and link queries), remains a barrier for non-technical users and hampers broader adoption.
To lower this barrier, we have developed a dedicated query interface powered by a custom-trained Large Language Model (LLM). The model is fine-tuned exclusively on a corpus of LinkAhead query pairs, consisting of a natural language description and a formal query. The system turns questions that users enter into LinkAhead into searches, handling both easy lookups and complex connections, without users needing to learn the query language.
In this presentation, we will describe the prototype’s design and present preliminary validation results that assess the model’s quality.
Registration for the event is not necessary, but possible so we can send you materials directly after the event and inform you of any changes.
This event is part of the Data Days Niedersachsen 2025 - Virtual Theme Day. An overview of the entire program can be found here:
https://fdm-nds.de/index.php/data-days-2025/
---
Die Veranstaltung wird von der Landesinitiative Forschungsdatenmanagement Niedersachsen (FDM-NDS) organisiert. FDM-NDS ist ein Verbundprojekt unter dem Dach der Hochschule.digital Niedersachsen und wird im Rahmen von zukunft.niedersachsen, einem Förderprogramm von Niedersächsischem Ministerium für Wissenschaft und Kultur (MWK) und VolkswagenStiftung gefördert.
