explainability
Explainability concerns the techniques used to interpret and clarify how AI models arrive at their predictions or decisions. This is crucial for building trust and ensuring accountability, particularly in critical applications.
- $\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection
- A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
- AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation
- Causally Reliable Concept Bottleneck Models
- Contimask: Explaining Irregular Time Series via Perturbations in Continuous Time
- Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
- DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
- ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
- GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
- GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
- Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model
- Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding
- Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
- Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions
- Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
- Sound Logical Explanations for Mean Aggregation Graph Neural Networks
- iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning