Papers by Giuseppe Gallipoli
Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive performance across various tasks, but current training approaches combine cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance performance. |
| Approach: | They evaluate the use of established semantic segmentation loss functions in natural language generation to create a versatile, practical, and scalable solution for fine-tuning different architectures. |
| Outcome: | The proposed models improve on Math Word Problems and question answering tasks without additional data or human feedback. |
It is not a piece of cake for GPT: Explaining Textual Entailment Recognition in the presence of Figurative Language (2025.coling-main)
Copied to clipboard
| Challenge: | Figure-based language is used to convey opinions, ideas, or emotions in texts and dialogues. |
| Approach: | They evaluate the capabilities of Large Language Models to address TER and generate textual explanations of TER predictions. |
| Outcome: | The proposed model outperforms the open-source models in Zero- and Few-Shot Learning settings and shows significant performance improvements. |