Friday 10 October 2025 - 11am Speaker: Adi Simhi (Technion, Israel Institute of Technology)Title: Characterizing Hallucinations: A Two-Dimensional Analysis of Knowledge and CertaintyAbstract: Hallucinations in Large Language Models (LLMs) present challenges beyond simple knowledge gaps. This work investigates hallucinations that occur despite models possessing correct information, examining two key studies: Distinguishing Ignorance from Error in LLM Hallucinations and Trust Me, I'm Wrong: High-Certainty Hallucinations in LLMs.We address whether hallucinations can manifest when models know correct answers, developing methodologies to isolate hallucination-despite-knowledge cases from ignorance-based errors. This distinction proves crucial for mitigation. We then investigate whether hallucinations despite knowledge can occur with high certainty, finding that such high-certainty hallucinations exist and occur consistently. These findings challenge current uncertainty-based detection and mitigation methods. Lastly, we provide a novel way to evaluate mitigation methods.Biography: Adi Simhi is a third-year PhD student in Yonatan Belinkov's lab at the Technion. Her research focuses on hallucinations and safety in LLMs. She received her Master's degree from the Technion under Shaul Markovitch. Oct 10 2025 11.00 - 12.00 Friday 10 October 2025 - 11am Speaker: Adi Simhi (Technion, Israel Institute of Technology) IF, G.03
Friday 10 October 2025 - 11am Speaker: Adi Simhi (Technion, Israel Institute of Technology)Title: Characterizing Hallucinations: A Two-Dimensional Analysis of Knowledge and CertaintyAbstract: Hallucinations in Large Language Models (LLMs) present challenges beyond simple knowledge gaps. This work investigates hallucinations that occur despite models possessing correct information, examining two key studies: Distinguishing Ignorance from Error in LLM Hallucinations and Trust Me, I'm Wrong: High-Certainty Hallucinations in LLMs.We address whether hallucinations can manifest when models know correct answers, developing methodologies to isolate hallucination-despite-knowledge cases from ignorance-based errors. This distinction proves crucial for mitigation. We then investigate whether hallucinations despite knowledge can occur with high certainty, finding that such high-certainty hallucinations exist and occur consistently. These findings challenge current uncertainty-based detection and mitigation methods. Lastly, we provide a novel way to evaluate mitigation methods.Biography: Adi Simhi is a third-year PhD student in Yonatan Belinkov's lab at the Technion. Her research focuses on hallucinations and safety in LLMs. She received her Master's degree from the Technion under Shaul Markovitch. Oct 10 2025 11.00 - 12.00 Friday 10 October 2025 - 11am Speaker: Adi Simhi (Technion, Israel Institute of Technology) IF, G.03
Oct 10 2025 11.00 - 12.00 Friday 10 October 2025 - 11am Speaker: Adi Simhi (Technion, Israel Institute of Technology)