3 papers
cs.CY2025
LLM-Generated Ads: From Personalization Parity to Persuasion Superiority
Elyas Meguellati, Stefano Civelli, Lei Han +3
As large language models (LLMs) become increasingly capable of generating persuasive content, understanding their effectiveness across different advertising strategies becomes crit…
cs.CL2025
LLM-based Semantic Augmentation for Harmful Content Detection
Elyas Meguellati, Assaad Zeghina, Shazia Sadiq +1
Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their effica…
cs.CL2025
Are Large Language Models Good Data Preprocessors?
Elyas Meguellati, Nardiena Pratama, Shazia Sadiq +1
High-quality textual training data is essential for the success of multimodal data processing tasks, yet outputs from image captioning models like BLIP and GIT often contain errors…