Papers by Giovanni Servedio
LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing (2025.acl-long)
Copied to clipboard
Dario Di Palma, Alessandro De Bellis, Giovanni Servedio, Vito Walter Anelli, Fedelucio Narducci, Tommaso Di Noia
| Challenge: | Large Language Models (LLMs) have become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques. |
| Approach: | They probe the hidden layers of Large Language Models to identify where sentiment features are most represented and to assess how this affects sentiment analysis. |
| Outcome: | The proposed approach enables sentiment tasks to be performed with memory requirements reduced by an average of 57%. |
Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models (2025.emnlp-main)
Copied to clipboard
Alessandro De Bellis, Salvatore Bufi, Giovanni Servedio, Vito Walter Anelli, Tommaso Di Noia, Eugenio Di Sciascio
| Challenge: | Existing methods to predict links between entities are limited in dynamic environments where new entities are incrementally introduced. |
| Approach: | They propose a Type-less yet type-awaRe approach for subgraph-based inductive link prediction that leverages pre-trained language models for semantic enrichment. |
| Outcome: | The proposed approach outperforms state-of-the-art models in scenarios with scarce type annotations and sparse graph connectivity. |
Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies suggest that LLMs encode internal representations of factuality when generating inaccurate or fabricated content. |
| Approach: | They propose a strategy for sampling plausible true-false factoid sentences from tabular data and a procedure for generating realistic, LLM-dependent true-False datasets from Question Answering collections. |
| Outcome: | The proposed approach lays the groundwork for future research on factuality in LLMs and offers practical guidelines for more effective evaluation. |