ai alignment

From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLMs EACL 2026 Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy ACL 2026 Intrinsic Barriers and Practical Pathways for Human–AI Alignment: An Agreement-Based Complexity Analysis AAAI 2026 Scaling Up AI Alignment AAAI 2026 Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment ACL 2026 An Evolutionary Perspective on AI Alignment (Student Abstract) AAAI 2025 Arbiters of Ambivalence: Challenges of using LLMs in No-Consensus tasks ACL 2025 Axioms for AI Alignment from Human Feedback AAAI 2025 Chat Bankman-Fried: an Exploration of LLM Alignment in Finance COLING 2025 Correcting Large Language Model Behavior via Influence Function AAAI 2025 Debate Helps Weak-to-Strong Generalization AAAI 2025 How to Mitigate Overfitting in Weak-to-strong Generalization? ACL 2025 Leveraging Human Input to Enable Robust, Interactive, and Aligned AI Systems AAAI 2025 princi/pal: A Moral Dilemma Tamagotchi Game NeurIPS 2025 PROTECT: Policy-Related Organizational Value Taxonomy for Ethical Compliance and Trust ACL 2025 Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment AAAI 2025 Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking ICLR 2025 Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization ICLR 2025 Towards a Theory of AI Personhood AAAI 2025 A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning NeurIPS 2024 Axioms for AI Alignment from Human Feedback NeurIPS 2024 Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints ICLR 2024 Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies NeurIPS 2024 Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision NeurIPS 2024 Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis ICLR 2024