{"total":18,"rows":[{"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":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"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":"2412.06438","title":"Can foundation models actively gather information in interactive environments to test hypotheses?","created":"2024-12-09","cited_by_count":8,"area":null},{"id":"2502.10308","title":"LLM-Powered Preference Elicitation in Combinatorial Assignment","created":"2025-02-14","cited_by_count":8,"area":null},{"id":"2502.01118","title":"Large Language Model-Enhanced Multi-Armed Bandits","created":"2025-02-03","cited_by_count":7,"area":null},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2507.15290","title":"Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2509.24701","title":"FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2402.15441","title":"Active Few-Shot Fine-Tuning","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2603.19221","title":"Online Learning and Equilibrium Computation with Ranking Feedback","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2410.07812","title":"Temporal-Difference Variational Continual Learning","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2504.02646","title":"Prompt Optimization with Logged Bandit Data","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2601.12945","title":"A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2407.12178","title":"Exploration Unbound","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2605.09075","title":"Optimality of Sub-network Laplace Approximations: New Results and Methods","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.11328","title":"Epistemic Uncertainty for Test-Time Discovery","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2610.08761","title":"VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}