Papers by Luca Cagliero
Detecting and Mitigating Challenges in Zero-Shot Video Summarization with Video LLMs (2025.findings-acl)
Copied to clipboard
Luca Cagliero, Lorenzo Vaiani, Eliana Pastor, Alkis Koudounas, Elena Baralis, Vittorio Mazzia, Sandro Pollastrini, Thomas Gueudre, Manuel Giollo, Daniele Amberti, Yue Wu
| Challenge: | Video Large Language Models (VLLMs) exhibit impressive zero-shot capabilities in video analysis, but their performance varies significantly depending on the LLM prompt, the characteristics of the video, and the properties of the training data and LLM architecture. |
| Approach: | They propose to use Chain-of-Thought prompting to inject knowledge extracted by external, lightweight models into video summarization benchmarks to evaluate their performance. |
| Outcome: | The proposed solutions improve summarization performance by injecting knowledge extracted by external, lightweight models. |
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. |
3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models for visually rich document understanding do not account for the diverse carriers of document versions and their associated noises. |
| Approach: | They propose a multimodal, multi-task, multiteacher joint-grained knowledge distillation model for visually-rich form document understanding. |
| Outcome: | The proposed model outperforms baselines on a comprehensive evaluation of public datasets showing it can handle complex structures and content of visually-rich forms. |
SQUAB: Evaluating LLM robustness to Ambiguous and Unanswerable Questions in Semantic Parsing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Practical user questions often deviate from ideal conditions, challenging the applicability of existing benchmarks. |
| Approach: | They propose an automatic dataset generator of Ambiguous and Unanswerable questions that generates complex, annotated SP tests using a blend of SQL and LLM capabilities. |
| Outcome: | The proposed framework reduces test generation costs by up to 99% while aligning with real-world question patterns. |
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. |
Privacy Preserving Data Selection for Bias Mitigation in Speech Models (2025.acl-industry)
Copied to clipboard
Alkis Koudounas, Eliana Pastor, Vittorio Mazzia, Manuel Giollo, Thomas Gueudre, Elisa Reale, Luca Cagliero, Sandro Cumani, Luca De Alfaro, Elena Baralis, Daniele Amberti
| Challenge: | Existing methods for identifying subgroups raise privacy concerns and gather sensitive information at runtime might be impractical. |
| Approach: | They propose a method to identify and train underperforming subgroups and train a model to predict if an utterance belongs to these subgroup. |
| Outcome: | The proposed method reduces biases and improves performance on intent classification and automatic speech recognition tasks. |