← Search

Giuseppe Gallipoli

2 accepted papers

2025

It is not a piece of cake for GPT: Explaining Textual Entailment Recognition in the presence of Figurative Language

COLING 2025main

Textual Entailment Recognition (TER) aims to predict whether a pair of premise-hypothesis sentences represents an entailment, a contradiction, or none of the above. Addressing TER in the presence of figurative language is particularly challenging because words are used in a way that deviates from th…

Cited by 1SourcePDFScholar
2024

Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning

EMNLP 2024finding

Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance performance. These solutions are often not scalable or feasible due t…