{"total":123,"rows":[{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2504.15236","title":"Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions","created":"2025-04-21","cited_by_count":52,"area":null},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"area":null},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2503.08663","title":"Generating Robot Constitutions & Benchmarks for Semantic Safety","created":"2025-03-11","cited_by_count":33,"area":null},{"id":"2409.09013","title":"AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents","created":"2024-09-13","cited_by_count":31,"area":"agents"},{"id":"2505.11413","title":"CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs","created":"2025-05-16","cited_by_count":26,"area":"safety"},{"id":"2505.24535","title":"Beyond Linear Steering: Unified Multi-Attribute Control for Language Models","created":"2025-05-30","cited_by_count":25,"area":null},{"id":"2501.00192","title":"MLLM-as-a-Judge for Image Safety without Human Labeling","created":"2024-12-31","cited_by_count":23,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2506.12657","title":"Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics","created":"2025-06-14","cited_by_count":19,"area":null},{"id":"2408.11441","title":"Epistemic Injustice in Generative AI","created":"2024-08-21","cited_by_count":16,"area":null},{"id":"2407.08867","title":"Perceptions of Sentient AI and Other Digital Minds: Evidence from the AI, Morality, and Sentience (AIMS) Survey","created":"2024-07-11","cited_by_count":15,"area":null},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2502.15861","title":"C3AI: Crafting and Evaluating Constitutions for Constitutional AI","created":"2025-02-21","cited_by_count":13,"area":"alignment"},{"id":"2510.07686","title":"Stress-Testing Model Specs Reveals Character Differences among Language Models","created":"2025-10-09","cited_by_count":13,"area":null},{"id":"2409.09041","title":"Acceptable Use Policies for Foundation Models","created":"2024-08-29","cited_by_count":12,"area":null},{"id":"2410.04715","title":"Selection of LLM Fine-Tuning Data based on Orthogonal Rules","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2412.03822","title":"Beyond the Binary: Capturing Diverse Preferences With Reward Regularization","created":"2024-12-05","cited_by_count":11,"area":"alignment"},{"id":"2509.08494","title":"HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2406.20087","title":"ProgressGym: Alignment with a Millennium of Moral Progress","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2503.00940","title":"Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisions","created":"2025-03-02","cited_by_count":9,"area":null},{"id":"2410.23953","title":"Representative Social Choice: From Learning Theory to AI Alignment","created":"2024-10-31","cited_by_count":8,"area":"alignment"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2503.01894","title":"LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2407.18421","title":"Self-Directed Synthetic Dialogues and Revisions Technical Report","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2407.19760","title":"Legal Minds, Algorithmic Decisions: How LLMs Apply Constitutional Principles in Complex Scenarios","created":"2024-07-29","cited_by_count":7,"area":null},{"id":"2507.17216","title":"The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2508.19269","title":"Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models","created":"2025-08-22","cited_by_count":7,"area":null},{"id":"2510.14591","title":"Just-In-Time Objectives: A General Approach for Specialized AI Interactions","created":"2025-10-16","cited_by_count":7,"area":null},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2411.10912","title":"SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment","created":"2024-11-16","cited_by_count":6,"area":"alignment"},{"id":"2412.09988","title":"AI and the Future of Digital Public Squares","created":"2024-12-13","cited_by_count":6,"area":null},{"id":"2412.16325","title":"Towards Safe and Honest AI Agents with Neural Self-Other Overlap","created":"2024-12-20","cited_by_count":6,"area":"agents"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2512.03399","title":"Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2409.18203","title":"Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2412.04498","title":"Large Language Models in Politics and Democracy: A Comprehensive Survey","created":"2024-12-01","cited_by_count":5,"area":null},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2509.08858","title":"Decentralising LLM Alignment: A Case for Context, Pluralism, and Participation","created":"2025-09-09","cited_by_count":5,"area":"alignment"},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2408.01458","title":"Surveys Considered Harmful? Reflecting on the Use of Surveys in AI Research, Development, and Governance","created":"2024-07-26","cited_by_count":4,"area":null},{"id":"2503.05830","title":"AI-Enhanced Deliberative Democracy and the Future of the Collective Will","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2503.20995","title":"ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"id":"2605.30169","title":"Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2406.11598","title":"Understanding \"Democratization\" in NLP and ML Research","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2501.17899","title":"The Right to AI","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2504.03029","title":"Ontologies in Design: How Imagining a Tree Reveals Possibilites and Assumptions in Large Language Models","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2507.16679","title":"PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization","created":"2025-07-22","cited_by_count":3,"area":"alignment"},{"id":"2508.16982","title":"Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2512.10665","title":"On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity","created":"2025-12-11","cited_by_count":3,"area":"agents"},{"id":"2603.05801","title":"Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.08525","title":"Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2503.18962","title":"Representative Ranking for Deliberation in the Public Sphere","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2504.00289","title":"Do Chinese models speak Chinese languages?","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2504.06016","title":"The Hall of AI Fears and Hopes: Comparing the Views of AI Influencers and those of Members of the U.S. Public Through an Interactive Platform","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2504.06324","title":"From Stability to Inconsistency: A Study of Moral Preferences in LLMs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2506.13245","title":"A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2508.00138","title":"Co-Producing AI: Toward an Augmented, Participatory Lifecycle","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2602.11318","title":"The Consensus Trap: Dissecting Subjectivity and the \"Ground Truth\" Illusion in Data Annotation","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2603.13189","title":"LLM Constitutional Multi-Agent Governance","created":"2026-03-13","cited_by_count":2,"area":"agents"},{"id":"2603.15968","title":"MAC: Multi-Agent Constitution Learning","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2604.10673","title":"Principles Do Not Apply Themselves: A Hermeneutic Perspective on AI Alignment","created":"2026-04-12","cited_by_count":2,"area":"alignment"},{"id":"2604.11838","title":"A Layer-wise Analysis of Supervised Fine-Tuning","created":"2026-04-12","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":"2411.10534","title":"Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment","created":"2024-11-15","cited_by_count":1,"area":"alignment"},{"id":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2503.01985","title":"Proportional Committee Elections with Positive and Negative Votes","created":"2025-03-03","cited_by_count":1,"area":null},{"id":"2504.15125","title":"Contemplative Artificial Intelligence","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2506.00195","title":"Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences","created":"2025-05-30","cited_by_count":1,"area":"alignment"},{"id":"2509.12626","title":"DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow","created":"2025-09-16","cited_by_count":1,"area":"agents"},{"id":"2509.25492","title":"Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations","created":"2025-09-29","cited_by_count":1,"area":"agents"},{"id":"2510.20612","title":"Black Box Absorption: LLMs Undermining Innovative Ideas","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2510.23631","title":"Beyond Pairwise: Empowering LLM Alignment With Ranked Choice Modeling","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2511.05804","title":"Catching Contamination Before Generation: Spectral Kill Switches for Agents","created":"2025-11-08","cited_by_count":1,"area":"lr"},{"id":"2602.07259","title":"Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.14940","title":"Kami of the Commons: Towards Designing Agentic AI to Steward the Commons","created":"2026-02-16","cited_by_count":1,"area":"agents"},{"id":"2604.17663","title":"ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2606.09475","title":"Emergent alignment and the projectability of ethical personas","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2503.15205","title":"A Peek Behind the Curtain: Using Step-Around Prompt Engineering to Identify Bias and Misinformation in GenAI Models","created":"2025-03-19","cited_by_count":0,"area":"safety"},{"id":"2506.00415","title":"Wide Reflective Equilibrium in LLM Alignment: Bridging Moral Epistemology and AI Safety","created":"2025-05-31","cited_by_count":0,"area":"alignment"},{"id":"2506.06816","title":"How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2507.05187","title":"Infrastructuring Contestability: A Framework for Community-Defined AI Value Pluralism","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2507.09060","title":"CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment","created":"2025-07-11","cited_by_count":0,"area":"alignment"},{"id":"2507.13175","title":"Black Box Deployed -- Functional Criteria for Artificial Moral Agents in the LLM Era","created":"2025-07-17","cited_by_count":0,"area":"agents"},{"id":"2508.15110","title":"LLMs and Agentic AI in Insurance Decision-Making: Opportunities and Challenges For Africa","created":"2025-08-20","cited_by_count":0,"area":"agents"},{"id":"2509.19680","title":"PolicyPad: Collaborative Prototyping of LLM Policies","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2601.05904","title":"Can AI mediation improve democratic deliberation?","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2602.05113","title":"Democratic Preference Alignment via Sortition-Weighted RLHF","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","cited_by_count":0,"area":"alignment"},{"id":"2603.28123","title":"Does Claude's Constitution Have a Culture?","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.10557","title":"LLMs Should Incorporate Explicit Mechanisms for Human Empathy","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.16224","title":"\"Taking Stock at FAccT\": Using Participatory Design to Co-Create a Vision for the Fairness, Accountability and Transparency Community","created":"2026-04-17","cited_by_count":0,"area":null}],"next_cursor":"100"}