{"total":72,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2410.02584","title":"Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions","created":"2024-10-03","cited_by_count":51,"area":"agents"},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25,"area":"alignment"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"id":"2410.04197","title":"CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2407.02446","title":"Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling","created":"2024-07-02","cited_by_count":20,"area":"wm"},{"id":"2410.02504","title":"Dual Active Learning for Reinforcement Learning from Human Feedback","created":"2024-10-03","cited_by_count":20,"area":"alignment"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2407.07089","title":"Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic","created":"2024-07-09","cited_by_count":14,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2505.20627","title":"Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching","created":"2025-05-27","cited_by_count":10,"area":"alignment"},{"id":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","cited_by_count":10,"area":"alignment"},{"id":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10,"area":"alignment"},{"id":"2606.15455","title":"Understanding Diversity Collapse in RLVR via the Lens of Overtraining","created":"2026-06-13","cited_by_count":10,"area":"lr"},{"id":"2506.04721","title":"SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat","created":"2025-06-05","cited_by_count":9,"area":"alignment"},{"id":"2504.19342","title":"Contextual Online Uncertainty-Aware Preference Learning for Human Feedback","created":"2025-04-27","cited_by_count":7,"area":"alignment"},{"id":"2506.01332","title":"An Empirical Study of Group Conformity in Multi-Agent Systems","created":"2025-06-02","cited_by_count":7,"area":"agents"},{"id":"2506.12350","title":"Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory","created":"2025-06-14","cited_by_count":7,"area":"alignment"},{"id":"2502.00657","title":"LLM Safety Alignment is Divergence Estimation in Disguise","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2602.16201","title":"Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2601.15755","title":"Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMs","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2601.23096","title":"CATTO: Balancing Preferences and Confidence in Language Models","created":"2026-01-30","cited_by_count":4,"area":"alignment"},{"id":"2603.03336","title":"Prompt-Dependent Ranking of Large Language Models with Uncertainty Quantification","created":"2026-02-11","cited_by_count":4,"area":"alignment"},{"id":"2603.17218","title":"Alignment Makes Language Models Normative, Not Descriptive","created":"2026-03-17","cited_by_count":4,"area":"alignment"},{"id":"2603.23301","title":"Steering LLMs for Culturally Localized Generation","created":"2026-03-24","cited_by_count":4,"area":"mechinterp"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2604.12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","cited_by_count":3,"area":"alignment"},{"id":"2512.00709","title":"When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF","created":"2025-11-30","cited_by_count":3,"area":"alignment"},{"id":"2512.03057","title":"A note on conditional PAC-efficient reasoning in large language model routing","created":"2025-11-25","cited_by_count":3,"area":"lr"},{"id":"2601.20838","title":"Reward Models Inherit Value Biases from Pretraining","created":"2026-01-28","cited_by_count":3,"area":"alignment"},{"id":"2503.07806","title":"Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models","created":"2025-03-10","cited_by_count":2,"area":"alignment"},{"id":"2503.17965","title":"Understanding the Effects of RLHF on the Quality and Detectability of LLM-Generated Texts","created":"2025-03-23","cited_by_count":2,"area":"alignment"},{"id":"2511.12804","title":"The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation","created":"2025-11-16","cited_by_count":2,"area":"alignment"},{"id":"2601.00747","title":"The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving","created":"2026-01-02","cited_by_count":2,"area":"lr"},{"id":"2605.04344","title":"Perturbation is All You Need for Extrapolating Language Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.11845","title":"Probabilistic Calibration Is a Trainable Capability in Language Models","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.25358","title":"AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.21550","title":"AI Alignment From Social Choice Perspectives","created":"2026-06-19","cited_by_count":2,"area":"alignment"},{"id":"2509.16462","title":"Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs","created":"2025-09-19","cited_by_count":1,"area":"safety"},{"id":"2511.05407","title":"Minority-Aware Satisfaction Estimation in Dialogue Systems via Preference-Adaptive Reinforcement Learning","created":"2025-11-07","cited_by_count":1,"area":"alignment"},{"id":"2511.07669","title":"Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2601.12758","title":"VISPA: Pluralistic Alignment via Automatic Value Selection and Activation","created":"2026-01-19","cited_by_count":1,"area":"alignment"},{"id":"2602.06665","title":"Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.18411","title":"TARo: Token-level Adaptive Routing for LLM Test-time Alignment","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2605.16193","title":"Improving Cross-Cultural Survey Simulation with Calibrated Value Personas","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2608.07367","title":"People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2508.06443","title":"The Fair Game: Auditing & Debiasing AI Algorithms Over Time","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2508.19567","title":"Counterfactual Reward Model Training for Bias Mitigation in Multimodal Reinforcement Learning","created":"2025-08-27","cited_by_count":0,"area":"alignment"},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2511.18933","title":"Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2601.06108","title":"From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models","created":"2026-01-03","cited_by_count":0,"area":"alignment"},{"id":"2602.11220","title":"Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT","created":"2026-02-11","cited_by_count":0,"area":"agents"},{"id":"2604.23543","title":"Pref-CTRL: Preference Driven LLM Alignment using Representation Editing","created":"2026-04-26","cited_by_count":0,"area":"alignment"},{"id":"2605.13284","title":"Learning Perturbations to Extrapolate Your LLM","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.26397","title":"Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2606.01382","title":"Efficient Exploration for Iterative Nash Preference Optimization","created":"2026-05-31","cited_by_count":0,"area":"alignment"},{"id":"2606.02741","title":"Greener Than Humans? Environmental Attitudes in Large Language Models","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.03165","title":"Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2606.07988","title":"PAFO: Pareto Fairness Optimization for Personalized Reward Modeling","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2608.07419","title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.08422","title":"Population-Level Generative Modeling for Ranking Data","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.15078","title":"Enabling Creative Exploration for Vibe Design Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.35044","title":"BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}