{"total":55,"rows":[{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"id":"2510.01135","title":"Prompt Curriculum Learning for Efficient LLM Post-Training","created":"2025-10-01","cited_by_count":45,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2502.14855","title":"Prompt-to-Leaderboard","created":"2025-02-20","cited_by_count":30,"area":null},{"id":"2306.00074","title":"Human-Aligned Calibration for AI-Assisted Decision Making","created":"2023-05-31","cited_by_count":28,"area":null},{"id":"2312.04782","title":"Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs","created":"2023-12-08","cited_by_count":27,"area":null},{"id":"2404.06013","title":"Feel-Good Thompson Sampling for Contextual Dueling Bandits","created":"2024-04-09","cited_by_count":27,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2305.14702","title":"DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"area":null},{"id":"2505.14826","title":"FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain","created":"2025-05-20","cited_by_count":15,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2405.02612","title":"Learning Linear Utility Functions From Pairwise Comparison Queries","created":"2024-05-04","cited_by_count":8,"area":null},{"id":"2411.08243","title":"Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset","created":"2024-11-12","cited_by_count":8,"area":null},{"id":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2312.01057","title":"RLHF and IIA: Perverse Incentives","created":"2023-12-02","cited_by_count":6,"area":null},{"id":"2405.03059","title":"Active Preference Learning for Ordering Items In- and Out-of-sample","created":"2024-05-05","cited_by_count":6,"area":null},{"id":"2407.18488","title":"Conversational Dueling Bandits in Generalized Linear Models","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2307.11288","title":"Kernelized Offline Contextual Dueling Bandits","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2310.06176","title":"Factual and Personalized Recommendations using Language Models and Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2311.09136","title":"Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2402.12617","title":"Generative AI Security: Challenges and Countermeasures","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2505.01954","title":"Semantic Probabilistic Control of Language Models","created":"2025-05-04","cited_by_count":4,"area":null},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2502.02079","title":"Online Clustering of Dueling Bandits","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2503.14203","title":"Stochastic Trajectory Prediction under Unstructured Constraints","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2312.12457","title":"Let AI Entertain You: Increasing User Engagement with Generative AI and Rejection Sampling","created":"2023-12-16","cited_by_count":2,"area":null},{"id":"2410.11330","title":"Evolutionary Retrofitting","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2502.01085","title":"Federated Linear Dueling Bandits","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2505.11983","title":"Online Iterative Self-Alignment for Radiology Report Generation","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2510.12121","title":"Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing","created":"2025-10-14","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":"2604.01206","title":"RELISH: LLM REgression with a Latent Iterative State Head","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2306.08001","title":"A Markovian Formalism for Active Querying","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2402.13079","title":"Mode Estimation with Partial Feedback","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2402.16792","title":"Rate-Optimal Rank Aggregation with Private Pairwise Rankings","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2403.06267","title":"FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers' Preference Elicitation","created":"2024-03-10","cited_by_count":1,"area":null},{"id":"2403.08199","title":"Deep Submodular Peripteral Networks","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2606.27082","title":"Finding Stationary Points by Comparisons","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2401.00330","title":"Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2501.06376","title":"Robustness in the Face of Partial Identifiability in Reward Learning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2501.07437","title":"Pairwise Comparisons without Stochastic Transitivity: Model, Theory and Applications","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2509.24493","title":"Preference-Based Dynamic Ranking Structure Recognition","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2601.19055","title":"Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2606.08410","title":"Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2609.39351","title":"On the Complexity of Preference-Based Bandits","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05428","title":"Learning in Continuous Games from Pairwise Preference Feedback","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.17203","title":"Online LLM Personalization from Pairwise Preferences Across Users","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17956","title":"Learning Distributions from Samples and Qualities","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}