← Search

Dario Di Palma

2 accepted papers

2025

Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs

ACL 2025long

Factual hallucinations are a major challenge for Large Language Models (LLMs). They undermine reliability and user trust by generating inaccurate or fabricated content. Recent studies suggest that when generating false statements, the internal states of LLMs encode information about truthfulness. Ho…

Cited by 0SourcePDFScholar
2025

LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing

ACL 2025long

Large Language Models (LLMs) have rapidly become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques, including sentiment analysis. However, we still have a limited understanding of how these models capture sentiment-related information. This study prob…

Cited by 0SourcePDFScholar