Ali Payani

Effective Guidance for Model Attention with Simple Yes-no Annotations

2024

Modern deep learning models often make predictions by focusing on irrelevant areas, leading to biased performance and limited generalization. Existing methods aimed at rectifying model attention require explicit labels for irrelevant areas or complex pixel-wise …

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity

2025

Hallucination in large language models (LLMs) can be detected by assessing the uncertainty of model outputs, typically measured using entropy.Semantic entropy (SE) enhances traditional entropy estimation by quantifying uncertainty at the semantic cluster level.However, as …