ArTLLaMA: Adaptating LLaMA to Performative Art Applications

Simple item page
dc.contributor.authorPassone, Elisaen_US
dc.contributor.authorBorazio, Federicoen_US
dc.contributor.authorHromei, Claudiu Danielen_US
dc.contributor.authorCroce, Daniloen_US
dc.contributor.authorBasili, Robertoen_US
dc.contributor.editorCampana, Stefanoen_US
dc.contributor.editorFerdani, Danieleen_US
dc.contributor.editorGraf, Holgeren_US
dc.contributor.editorGuidi, Gabrieleen_US
dc.contributor.editorHegarty, Zackaryen_US
dc.contributor.editorPescarin, Sofiaen_US
dc.contributor.editorRemondino, Fabioen_US
dc.date.accessioned2025-09-05T20:05:58Z
dc.date.available2025-09-05T20:05:58Z
dc.date.issued2025
dc.description.abstractPerformative Arts represent a compelling and underexplored domain for the application of Generative AI, given their rich conceptual complexity and cultural depth. This paper presents ArTLLaMA, a domain-adapted version of the LLaMA language model, designed to support natural language querying of ArTBase, the first national database of Italian theatres and theatre archives. We focus on the Text-to-SQL task: automatically translating user questions into executable SQL queries. Off-the-shelf models often fail in this setting due to a lack of domain knowledge and schema awareness. To bridge this gap, we propose a two-stage fine-tuning methodology: first, we train the model to internalize the Entity-Relationship (ER) schema of ArTBase; then, we fine-tune it on a curated set of over 800 natural language-SQL query pairs reflecting real use cases in the domain. Our results show that schema-informed fine-tuning significantly boosts accuracy, with the best model achieving over 70% exact match andgenerating correct SQL even for complex queries involving multi-table joins and aggregations. Compared to general purpose models like ChatGPT, our approach yields more accurate, schema-compliant outputs. Beyond technical improvements, this work underscores the value of interdisciplinary collaboration: by embedding domain knowledge from the humanities into AI systems, we enable new forms of access, interaction, and understanding of cultural heritage data.en_US
dc.description.sectionheadersDigitization and Segmentation
dc.description.seriesinformationDigital Heritage
dc.identifier.doi10.2312/dh.20253113
dc.identifier.isbn978-3-03868-277-6
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/dh.20253113
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/dh20253113
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Artificial Intelligence → Machine learning; Natural Language Processing; Natural Language Generation
dc.subjectArtificial Intelligence → Machine learning
dc.subjectNatural Language Processing
dc.subjectNatural Language Generation
dc.titleArTLLaMA: Adaptating LLaMA to Performative Art Applicationsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
dh20253113.pdf
Size:
252.65 KB
Format:
Adobe Portable Document Format
Download
Collections
Track 04 – Acquisition and Digitization