ExtremITA at EVALITA 2023: Multi-Task Sustainable Scaling to Large Language Models at its Extreme

This paper explores the potential application of a monolithic neural model for all tasks in EVALITA 2023. We evaluated two models: extremIT5, an encoder-decoder model, and extremITLLaMA an instruction-tuned Decoder-only Large Language Model, specifically designed for handling Italian instructions. Our approach revolves around representing tasks in natural language, where we provide instructions to the model using prompts that define the expected responses. Remarkably, our best-performing model achieved first place in 41% of the subtasks and showcased top-three performance in 64%. These subtasks encompass various semantic dimensions, including Affect Detection, Authorship Analysis, Computational Ethics, Named Entity Recognition, Information Extraction, and Discourse Coherence.