{"total":120,"rows":[{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200,"area":"alignment"},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120,"area":null},{"id":"2305.14613","title":"Selectively Answering Ambiguous Questions","created":"2023-05-24","cited_by_count":66,"area":null},{"id":"2202.06985","title":"Deep Ensembles Work, But Are They Necessary?","created":"2022-02-14","cited_by_count":63,"area":null},{"id":"2211.06291","title":"Do Bayesian Neural Networks Need To Be Fully Stochastic?","created":"2022-11-11","cited_by_count":63,"area":null},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63,"area":"alignment"},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59,"area":null},{"id":"2402.03563","title":"Distinguishing the Knowable from the Unknowable with Language Models","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45,"area":null},{"id":"2412.20892","title":"Rethinking Aleatoric and Epistemic Uncertainty","created":"2024-12-30","cited_by_count":42,"area":null},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2505.11737","title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","created":"2025-05-16","cited_by_count":24,"area":"lr"},{"id":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22,"area":null},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","cited_by_count":22,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2206.03633","title":"Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping","created":"2022-06-08","cited_by_count":19,"area":null},{"id":"2307.05772","title":"Random-Set Neural Networks (RS-NN)","created":"2023-07-11","cited_by_count":19,"area":null},{"id":"2402.08733","title":"Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2406.10023","title":"Deep Bayesian Active Learning for Preference Modeling in Large Language Models","created":"2024-06-14","cited_by_count":19,"area":null},{"id":"2210.04994","title":"Sampling-based inference for large linear models, with application to linearised Laplace","created":"2022-10-10","cited_by_count":18,"area":null},{"id":"2305.15208","title":"Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2304.03646","title":"Fairness through Aleatoric Uncertainty","created":"2023-04-07","cited_by_count":16,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2406.00104","title":"Scalable Bayesian Learning with posteriors","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2302.08981","title":"Black-Box Batch Active Learning for Regression","created":"2023-02-17","cited_by_count":12,"area":null},{"id":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2301.12860","title":"Massively Scaling Heteroscedastic Classifiers","created":"2023-01-30","cited_by_count":11,"area":null},{"id":"2405.03164","title":"The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning","created":"2024-05-06","cited_by_count":11,"area":null},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11,"area":"alignment"},{"id":"2202.13509","title":"Evaluating High-Order Predictive Distributions in Deep Learning","created":"2022-02-28","cited_by_count":10,"area":null},{"id":"2211.01595","title":"Reinforcement Learning in Non-Markovian Environments","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2404.03099","title":"Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks","created":"2024-04-03","cited_by_count":10,"area":null},{"id":"2406.00332","title":"A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning","created":"2024-06-01","cited_by_count":10,"area":null},{"id":"2404.02649","title":"On the Importance of Uncertainty in Decision-Making with Large Language Models","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2412.18808","title":"Provable Uncertainty Decomposition via Higher-Order Calibration","created":"2024-12-25","cited_by_count":9,"area":null},{"id":"2305.11455","title":"Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models","created":"2023-05-19","cited_by_count":8,"area":"agents"},{"id":"2312.15576","title":"Reducing LLM Hallucinations using Epistemic Neural Networks","created":"2023-12-25","cited_by_count":8,"area":null},{"id":"2505.04950","title":"Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2207.01524","title":"Variational Neural Networks","created":"2022-07-04","cited_by_count":7,"area":null},{"id":"2207.09336","title":"Uncertainty in Contrastive Learning: On the Predictability of Downstream Performance","created":"2022-07-19","cited_by_count":7,"area":null},{"id":"2302.06544","title":"Probabilistic Circuits That Know What They Don't Know","created":"2023-02-13","cited_by_count":7,"area":null},{"id":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2110.04738","title":"Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2203.00246","title":"An Information-Theoretic Framework for Supervised Learning","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2302.08669","title":"Learning to Forecast Aleatoric and Epistemic Uncertainties over Long Horizon Trajectories","created":"2023-02-17","cited_by_count":6,"area":"wm"},{"id":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","cited_by_count":6,"area":"deeprl"},{"id":"2506.09270","title":"Uncertainty Prioritized Experience Replay","created":"2025-06-10","cited_by_count":6,"area":"deeprl"},{"id":"2308.06590","title":"Value-Distributional Model-Based Reinforcement Learning","created":"2023-08-12","cited_by_count":5,"area":null},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"2206.01085","title":"Incorporating Explicit Uncertainty Estimates into Deep Offline Reinforcement Learning","created":"2022-06-02","cited_by_count":4,"area":"offlinerl"},{"id":"2402.06963","title":"Tree Ensembles for Contextual Bandits","created":"2024-02-10","cited_by_count":4,"area":null},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2503.19333","title":"E-PINNs: Epistemic Physics-Informed Neural Networks","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2110.15907","title":"Learning to Be Cautious","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2205.08766","title":"Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2210.04882","title":"Layer Ensembles","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2406.09262","title":"Fully Heteroscedastic Count Regression with Deep Double Poisson Networks","created":"2024-06-13","cited_by_count":3,"area":null},{"id":"2406.10775","title":"A Rate-Distortion View of Uncertainty Quantification","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2409.03953","title":"Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2412.04323","title":"GRAM: Generalization in Deep RL with a Robust Adaptation Module","created":"2024-12-05","cited_by_count":3,"area":"deeprl"},{"id":"2205.11117","title":"PyRelationAL: a python library for active learning research and development","created":"2022-05-23","cited_by_count":2,"area":null},{"id":"2310.17493","title":"A Hybrid Graph Network for Complex Activity Detection in Video","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2404.19292","title":"Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2405.04043","title":"Scalable Vertical Federated Learning via Data Augmentation and Amortized Inference","created":"2024-05-07","cited_by_count":2,"area":null},{"id":"2406.12082","title":"Uncertainty modeling for fine-tuned implicit functions","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2410.14807","title":"Aligning AI Agents via Information-Directed Sampling","created":"2024-10-18","cited_by_count":2,"area":"alignment"},{"id":"2505.13501","title":"SPIEDiff: robust learning of long-time macroscopic dynamics from short-time particle simulations with quantified epistemic uncertainty","created":"2025-05-16","cited_by_count":2,"area":"diffusion"},{"id":"2505.22803","title":"CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2603.09692","title":"ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2608.23244","title":"Credal Large Language Models for Semantic Commitment under Uncertainty","created":"2026-08-24","cited_by_count":2,"area":null},{"id":"2209.15618","title":"Beyond Bayes-optimality: meta-learning what you know you don't know","created":"2022-09-30","cited_by_count":1,"area":null},{"id":"2310.01569","title":"Iterative Option Discovery for Planning, by Planning","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2402.02858","title":"Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning","created":"2024-02-05","cited_by_count":1,"area":"offlinerl"},{"id":"2402.10232","title":"Simple, unified analysis of Johnson-Lindenstrauss with applications","created":"2024-02-10","cited_by_count":1,"area":null},{"id":"2408.01301","title":"A Decision-driven Methodology for Designing Uncertainty-aware AI Self-Assessment","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2411.11935","title":"Calibrated and Efficient Sampling-Free Confidence Estimation for LiDAR Scene Semantic Segmentation","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2505.08988","title":"Generalization in Monitored Markov Decision Processes (Mon-MDPs)","created":"2025-05-13","cited_by_count":1,"area":"deeprl"},{"id":"2506.07088","title":"Pointwise confidence estimation in the non-linear $\\ell^2$-regularized least squares","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2506.16313","title":"Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2510.21691","title":"On Uncertainty Calibration for Equivariant Functions","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.00960","title":"Multimodal Scientific Learning Beyond Diffusions and Flows","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2604.07072","title":"Epistemic Robust Offline Reinforcement Learning","created":"2026-04-08","cited_by_count":1,"area":"offlinerl"},{"id":"2605.16383","title":"A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classification","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2111.11055","title":"Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model","created":"2021-11-22","cited_by_count":0,"area":null},{"id":"2207.00137","title":"Robustness of Epinets against Distributional Shifts","created":"2022-07-01","cited_by_count":0,"area":null},{"id":"2302.00284","title":"Selective Uncertainty Propagation in Offline RL","created":"2023-02-01","cited_by_count":0,"area":"offlinerl"},{"id":"2302.05914","title":"Variational Voxel Pseudo Image Tracking","created":"2023-02-12","cited_by_count":0,"area":null},{"id":"2312.07621","title":"Spatiotemporal Event Graphs for Dynamic Scene Understanding","created":"2023-12-11","cited_by_count":0,"area":null},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2410.10908","title":"The State of Julia for Scientific Machine Learning","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2507.01699","title":"Variational Graph Convolutional Neural Networks","created":"2025-07-02","cited_by_count":0,"area":null}],"next_cursor":"100"}