{"id":474,"date":"2026-03-31T14:51:09","date_gmt":"2026-03-31T14:51:09","guid":{"rendered":"https:\/\/www.sigenera.eu\/?page_id=474"},"modified":"2026-09-11T14:32:50","modified_gmt":"2026-09-11T14:32:50","slug":"work-packages-2","status":"publish","type":"page","link":"https:\/\/www.sigenera.eu\/en\/work-packages-2\/","title":{"rendered":"Work Packages"},"content":{"rendered":"
\n

<\/p>\n

\n
\n
\n <\/span>
\n WORK PACKAGES\n <\/div>\n

\n Project Structure<\/strong>
\n <\/h1>\n
<\/div>\n

\n The project is organized into 5 work packages: a shared platform, three vertical applications addressing the partners\u2019 use cases, and a work package dedicated to dissemination.\n <\/p>\n<\/p><\/div>\n

<\/p>\n

\n

<\/p>\n

\n \n \n \n <\/lineargradient>\n

\n \n <\/filter>\n <\/defs><\/p>\n

<\/p>\n\n \n \n <\/g><\/p>\n

\n \n \n \n \n \n \n \n <\/g><\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/g><\/p>\n

<\/p>\n

<\/svg><\/p><\/div>\n<\/section>\n

<\/p>\n

\n
01<\/div>\n
\n
\n
WP1<\/div>\n
\n LEAD ORGANIZATION: UNICAL\n <\/div>\n

SIGENERA Platform<\/h2>\n
<\/div>\n

\n Critical analysis of GenAI\/LLM techniques and implementation of the shared platform.\n <\/p>\n

<\/p>\n

\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n<\/p>\n

<\/p>\n

<\/p>\n

<\/svg><\/p><\/div>\n<\/p><\/div>\n

\n
\n
\n \n \n \n \n \n <\/svg>\n <\/div>\n
\n
A1.1<\/div>\n

State-of-the-Art Analysis<\/h3>\n

\n omprehensive analysis of available GenAI\/LLM technologies: fine-tuning, RAG, quantization, testing techniques, and methods for correcting undesirable behaviors.\n <\/p>\n<\/p><\/div>\n<\/article>\n

\n
\n <\/p>\n

<\/p>\n<\/p>\n<\/p>\n

<\/p>\n

<\/svg>\n <\/div>\n

\n
A1.2<\/div>\n

Platform Implementation<\/h3>\n

\n Design and implementation of the SIGENERA platform: scalable, featuring fine-tuning, querying, and advanced prompting techniques on GPUs.\n <\/p>\n<\/p><\/div>\n<\/article><\/div>\n<\/p><\/div>\n<\/section>\n

<\/p>\n

\n
02<\/div>\n
\n
\n
\n
\n \n \n \n \n \n \n <\/svg>\n <\/div>\n
\n
A2.1<\/div>\n

LLM Models for the Help Desk<\/h3>\n

\n Study of the theoretical foundations of Large Language Models (LLMs) for automated response systems. Customisation of the SIGENERA platform using data from the University of Calabria's Student Services, serving up to 50,000 students.\n <\/p>\n<\/p><\/div>\n<\/article>\n

\n
\n

<\/p>\n

<\/p>\n<\/p>\n

<\/p>\n

<\/svg><\/p><\/div>\n

\n
A2.2<\/div>\n

UNICAL Chatbot Development<\/h3>\n

\n Development of the chatbot to handle student enquiries, resolve common issues automatically, and route more complex requests to human operators, following an Agile development methodology.\n <\/p>\n<\/p><\/div>\n<\/article><\/div>\n

\n
WP2<\/div>\n
\n LEAD ORGANIZATION: UNICAL\n <\/div>\n

University Help Desk<\/h2>\n
<\/div>\n

\n Adaptation of the SIGENERA platform to the Help Desk chatbot for UNICAL\u2019s Educational Services M7\u2013M24 \u00b7 Type: RI, SS<\/span>\n <\/p>\n

\n

<\/p>\n

<\/p>\n<\/p>\n

<\/p>\n<\/p>\n<\/p>\n

<\/svg><\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/section>\n

<\/p>\n

\n
03<\/div>\n
\n
\n
WP3<\/div>\n
\n LEAD ORGANIZATION: Digiservice\n <\/div>\n

Source Code Generation<\/h2>\n
<\/div>\n

\n Adaptation of the platform for querying and monitoring information systems, applied to TimeSheet Connect and MyVisure. M7\u2013M24 \u00b7 Type: RI, SS<\/span>\n <\/p>\n

\n

<\/p>\n

<\/p>\n

\n <\/p>\n<\/p>\n<\/p>\n<\/p>\n

<\/p>\n<\/p>\n

<\/svg><\/p><\/div>\n<\/p><\/div>\n

\n
\n
\n

<\/p>\n<\/p>\n<\/p>\n

<\/svg><\/p><\/div>\n

\n
A3.1<\/div>\n

LLM Models for Information Systems Querying<\/h3>\n

\n Adaptation of LLM models for generating queries and commands in the DML of the MYVISURE information system (Tecnoinnovis) and TimeSheet Connect Q (Digiservice).\n <\/p>\n<\/p><\/div>\n<\/article>\n

\n
\n

<\/p>\n<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/svg><\/p><\/div>\n

\n
A3.2<\/div>\n

Software Services Development and Validation<\/h3>\n

\n Development of software modules to integrate LLM models into the target platforms. ITS CADMO interns will be involved in on-the-job training. AGILE methodology.\n <\/p>\n<\/p><\/div>\n<\/article><\/div>\n<\/p><\/div>\n<\/section>\n

<\/p>\n

\n
04<\/div>\n
\n
\n
\n
\n

<\/p>\n

<\/p>\n<\/p>\n<\/p>\n

<\/p>\n

<\/svg><\/p><\/div>\n

\n
A4.1<\/div>\n

LLM Models for Meeting Minutes Generation<\/h3>\n

\n Adaptation of LLM models for the automatic generation of meeting minutes within the EligoVote platform (ID Technology), using AI techniques to improve the accuracy, consistency, and reliability of the content.\n <\/p>\n<\/p><\/div>\n<\/article>\n

\n
\n

<\/p>\n

<\/p>\n

<\/p>\n<\/p>\n<\/p>\n

<\/svg><\/p><\/div>\n

\n
A4.2<\/div>\n

Software Services Development and Validation<\/h3>\n

\n Development of software services to integrate LLM models into the EligoVote platform through SiGENERA. The prototype will be validated using a dataset of transcripts and voting records. AGILE methodology.\n <\/p>\n<\/p><\/div>\n<\/article><\/div>\n

\n
WP4<\/div>\n
\n LEAD ORGANIZATION: ID Technology\n <\/div>\n

Meeting Minutes Generation<\/h2>\n
<\/div>\n

\n Verticalizzazione della piattaforma SIGENERA per la generazione automatica di verbali di riunione nella piattaforma EligoVote, mediante modelli LLM specializzati, tecniche di AI per il supporto contestuale e servizi software integrati per la produzione e la validazione dei verbali. M7\u2013M24 \u00b7 Type: RI, SS<\/span>\n <\/p>\n

\n

<\/p>\n

<\/p>\n<\/p>\n

<\/p>\n<\/p>\n

<\/p>\n

<\/svg><\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/section>\n

<\/p>\n

\n
05<\/div>\n
\n
\n
WP5<\/div>\n
\n LEAD ORGANIZATION: TECNOINNOVIS\n <\/div>\n

Dissemination of Results<\/h2>\n
<\/div>\n

\n Sharing the project\u2019s results with the scientific community and the general public through multiple channels. M1\u2013M24 \u00b7 Type: RI, SS<\/span>\n <\/p>\n

\n

<\/p>\n<\/p>\n<\/p>\n<\/p>\n<\/p>\n

<\/p>\n

<\/svg><\/p><\/div>\n<\/p><\/div>\n

\n
\n
\n

<\/p>\n<\/p>\n<\/p>\n<\/p>\n

<\/svg><\/p><\/div>\n

\n
A5.1<\/div>\n

Communication and Project Website<\/h3>\n

\n Regional workshop, brochure, infographics, bilingual website (IT\/EN), and promotion through professional social media channels, particularly LinkedIn.\n <\/p>\n<\/p><\/div>\n<\/article>\n

\n
\n

<\/p>\n

<\/p>\n<\/p>\n<\/p>\n

<\/svg><\/p><\/div>\n

\n
A5.2<\/div>\n

International Conferences<\/h3>\n

\n Participation in at least two international conferences in different EU Member States. Publication of articles in specialized ICT and FinTech journals\n <\/p>\n<\/p><\/div>\n<\/article><\/div>\n<\/p><\/div>\n<\/section>\n

<\/p>\n

\n
<\/div>\n
\n Five work packages,
\n one shared vision.<\/strong>\n <\/div>\n
\n Bringing Artificial Intelligence to serve people, organizations, and society.\n <\/div>\n


\n Discover the Project
\n \u2192<\/span>
\n <\/a><\/p>\n<\/section>\n<\/div>","protected":false},"excerpt":{"rendered":"

WORK PACKAGES Struttura del Progetto Il progetto si articola in 5 work package: una piattaforma comune e tre verticalizzazioni sui casi d\u2019uso dei partner, pi\u00f9 un WP dedicato alla divulgazione. 01 WP1 RESPONSABILE: UNICAL Piattaforma SIGENERA Analisi critica delle tecniche GenAI\/LLM e implementazione della piattaforma comune. A1.1 Analisi stato dell\u2019arte Analisi esaustiva delle tecnologie GenAI\/LLM disponibili: fine-tuning, RAG, quantizzazione, tecniche […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"footnotes":""},"class_list":["post-474","page","type-page","status-publish","hentry"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t