Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMs
Debarpan Bhattacharya, Apoorva Kulkarni, Sriram Ganapathy
The accurate trust assessment of multimodal large language models (MLLMs) generated predictions, which can enable selective prediction and improve user confidence, is challenging d…
cs.AI2024
Gradient-free Post-hoc Explainability Using Distillation Aided Learnable Approach
Debarpan Bhattacharya, Amir H. Poorjam, Deepak Mittal +1
The recent advancements in artificial intelligence (AI), with the release of several large models having only query access, make a strong case for explainability of deep models in…