model uncertainty

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations EMNLP 2024 Differentially private methods for managing model uncertainty in linear regression JMLR 2024 Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method NAACL 2024 Linguistic Obfuscation Attacks and Large Language Model Uncertainty EACL 2024 Monte Carlo Tree Search in the Presence of Transition Uncertainty AAAI 2024 Robust Active Measuring under Model Uncertainty AAAI 2024 Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation ACL 2023 Bayesian Optimization-Based Combinatorial Assignment AAAI 2023 Bayesian Risk-Averse Q-Learning with Streaming Observations NeurIPS 2023 Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures CVPR 2023 Causal Inference under Interference and Model Uncertainty CLeaR 2023 Constraining Representations Yields Models That Know What They Don't Know ICLR 2023 Decentralized Robust V-learning for Solving Markov Games with Model Uncertainty JMLR 2023 Finetuning Offline World Models in the Real World CoRL 2023 Retrieval-Augmented Parsing for Complex Graphs by Exploiting Structure and Uncertainty EMNLP 2023 Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning NeurIPS 2023 Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification NeurIPS 2023 Adapting the Linearised Laplace Model Evidence for Modern Deep Learning ICML 2022 ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation EMNLP 2022 Adversarial Robustness Guarantees for Gaussian Processes JMLR 2022 Bayesian Imitation Learning for End-to-End Mobile Manipulation ICML 2022 Bayesian Model Averaging of Chain Event Graphs for Robust Explanatory Modelling PGM 2022 Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation EMNLP 2022 From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models EMNLP 2022 Identifying Wrongly Predicted Samples: A Method for Active Learning WACV 2022