BEGIN:VCALENDAR VERSION:2.0 PRODID:-//CFP.DEV//CFP.DEV shortcodes//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-WR-CALNAME:Voxxed Days Ticino 2026 X-WR-RELCALID:c426493a-54d4-472b-b975-6f3aaa7163fa X-WR-TIMEZONE:Europe/Zurich BEGIN:VEVENT UID:cfp-1151-8681@cfp.dev DTSTAMP:20260920T122123Z SEQUENCE:0 STATUS:CONFIRMED DTSTART:20260206T141000Z DTEND:20260206T145500Z SUMMARY:Teaching Exotic Programming Languages to Large Language Models DESCRIPTION:Imagine asking a computer to build an entire app from scratch a nd it does\, instantly\, just by understanding your words. That is not sci ence fiction anymore. Large Language Models (LLMs) are reshaping how we wr ite software\, aiding developers and even non-developers alike in crafting code with unprecedented ease.But there is a catch. These models are fluen t in the world'\;s most popular programming languages\, like Python or Java\, and struggle when they face the dialects of industry: the in-house programming languages companies build for their own unique problems. LLMs often have little to no training knowledge of these languages\, which make s it difficult for them to assist in these specialized domains. For this r eason\, in-house programming languages are perceived as exotic by LLMs.In this talk\, I will share my experience in teaching new and exotic programm ing languages to LLMs. I will show the challenges we faced during the proc ess and how current techniques like retrieval-augmented generation\, few-s hot learning\, and fine-tuning open-weight models performed in this contex t. Finally\, I will share the "\;secret recipe"\; we used to succe ssfully teach these languages to LLMs\, enabling them to assist in coding tasks that were previously out of reach.\nSpeakers: Alessandro Giagnorio\n Track: Machine Learning & AI URL:https://vdt26.voxxeddays.ch/talk/teaching-exotic-programming-languages- to-large-language-models/ LOCATION:Room C\nPalazzo dei Congressi\nLugano\, Switzerland CATEGORIES:Machine Learning & AI END:VEVENT END:VCALENDAR