Yassine Benajiba

Active Evaluation Acquisition for Efficient LLM Benchmarking

Aligning to Constraints for Data-Efficient Language Model Customization

Active Evaluation Acquisition for Efficient LLM Benchmarking

DiverseAgentEntropy: Quantifying Black-Box LLM Uncertainty through Diverse Perspectives and Multi-Agent Interaction

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

Inference time LLM alignment in single and multidomain preference spectrum