6 papers
Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods
Mehrdad Fazli, Sina Mansouri, Mohit Marvania +1
Recent inference-time hallucination mitigation methods for large vision-language models (LVLMs) report strong gains on hallucination benchmarks. However, it remains unclear whether…
VeriSim: A Configurable Framework for Stress-Testing Medical AI Under Patient Communication Noise
Sina Mansouri, Mohit Marvania, Vibhavari Ashok Shihorkar +5
Medical large language models are typically evaluated on idealized patient cases that do not reflect how real patients communicate. We introduce VeriSim, a patient simulation frame…
Context-Aware Decoding for Faithful Vision-Language Generation
Mehrdad Fazli, Bowen Wei, Ziwei Zhu
Hallucinations, generating responses inconsistent with the visual input, remain a critical limitation of large vision-language models (LVLMs), especially in open-ended tasks such a…
Learning to Explain: Prototype-Based Surrogate Models for LLM Classification
Bowen Wei, Mehrdad Fazli, Ziwei Zhu
Large language models (LLMs) have demonstrated impressive performance on natural language tasks, but their decision-making processes remain largely opaque. Existing explanation met…
Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
Mehrdad Fazli, Bowen Wei, Ahmet Sari +1
Large vision-language models (LVLMs) achieve impressive performance on multimodal tasks but often suffer from hallucination, and confidently describe objects or attributes not pres…
HHAR-net: Hierarchical Human Activity Recognition using Neural Networks
Mehrdad Fazli, Kamran Kowsari, Erfaneh Gharavi +2
Activity recognition using built-in sensors in smart and wearable devices provides great opportunities to understand and detect human behavior in the wild and gives a more holistic…