XU-RS: Explaining Credal Width in Random-Set Language Models
cs.AI, stat.ML
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Credal and Interval Deep Evidential Classifications
- Belief likelihood function for generalised logistic regression
- Visions of a generalized probability theory
- Uncertainty measures: The big picture
- Reasoning with random sets: An agenda for the future
- Generalising realisability in statistical learning theory under epistemic uncertainty
- Statistical inference with belief functions: A survey
- ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models
- Epistemic Deep Learning
- Random-Set Neural Networks (RS-NN)
- Uncertainty-Aware Autonomous Vehicles: Predicting the Road Ahead
- Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'
- A Unified Evaluation Framework for Epistemic Predictions
- Credal Large Language Models for Semantic Commitment under Uncertainty
- Epistemic Generative Adversarial Networks
- Random-Set Large Language Models
- Epistemic Monte Carlo Tree Search
- Epistemic Wrapping for Uncertainty Quantification
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Learning Credal Ensembles via Distributionally Robust Optimization
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection