{"total":144,"rows":[{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113,"area":"alignment"},{"id":"2406.11657","title":"Can LLM be a Personalized Judge?","created":"2024-06-17","cited_by_count":100,"area":null},{"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":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2510.06552","title":"Flipping the Dialogue: Training and Evaluating User Language Models","created":"2025-10-08","cited_by_count":58,"area":null},{"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":"2405.19534","title":"Preference Learning Algorithms Do Not Learn Preference Rankings","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2603.03303","title":"HumanLM: Simulating Users with State Alignment Beats Response Imitation","created":"2026-02-07","cited_by_count":37,"area":null},{"id":"2410.03868","title":"Can Language Models Reason about Individualistic Human Values and Preferences?","created":"2024-10-04","cited_by_count":34,"area":"lr"},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2502.08395","title":"IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance","created":"2025-02-12","cited_by_count":26,"area":null},{"id":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2508.01674","title":"CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions","created":"2025-08-03","cited_by_count":22,"area":null},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2505.14633","title":"Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas","created":"2025-05-20","cited_by_count":18,"area":null},{"id":"2507.04607","title":"PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process","created":"2025-07-07","cited_by_count":18,"area":"lr"},{"id":"2412.11167","title":"Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette","created":"2024-12-15","cited_by_count":16,"area":"agents"},{"id":"2502.19312","title":"FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users","created":"2025-02-26","cited_by_count":15,"area":"alignment"},{"id":"2505.12158","title":"The AI Gap: How Socioeconomic Status Affects Language Technology Interactions","created":"2025-05-17","cited_by_count":15,"area":null},{"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":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"id":"2510.05931","title":"Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2603.23231","title":"PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2606.14199","title":"OdysSim: Building Foundation Models for Human Behavior Simulation","created":"2026-06-12","cited_by_count":13,"area":null},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2406.15352","title":"A SMART Mnemonic Sounds like \"Glue Tonic\": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick","created":"2024-06-21","cited_by_count":10,"area":"alignment"},{"id":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","cited_by_count":10,"area":"alignment"},{"id":"2501.18045","title":"From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphors","created":"2025-01-29","cited_by_count":10,"area":null},{"id":"2506.07326","title":"Reward Model Interpretability via Optimal and Pessimal Tokens","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2507.13579","title":"Learning to summarize user information for personalized reinforcement learning from human feedback","created":"2025-07-17","cited_by_count":10,"area":"alignment"},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2506.18082","title":"Statistical Multicriteria Evaluation of LLM-Generated Text","created":"2025-06-22","cited_by_count":9,"area":null},{"id":"2408.08291","title":"The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community","created":"2024-08-15","cited_by_count":8,"area":null},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2506.05305","title":"ProRefine: Inference-Time Prompt Refinement with Textual Feedback","created":"2025-06-05","cited_by_count":8,"area":"agents"},{"id":"2509.22957","title":"Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2503.23688","title":"Mapping Geopolitical Bias in 11 Large Language Models: A Bilingual, Dual-Framing Analysis of U.S.-China Tensions","created":"2025-03-31","cited_by_count":7,"area":null},{"id":"2509.24696","title":"T-POP: Test-Time Personalization with Online Preference Feedback","created":"2025-09-29","cited_by_count":7,"area":"alignment"},{"id":"2512.01351","title":"Benchmarking Overton Pluralism in LLMs","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2604.07343","title":"Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization","created":"2026-04-08","cited_by_count":7,"area":"alignment"},{"id":"2606.19336","title":"Learning User Simulators with Turing Rewards","created":"2026-06-17","cited_by_count":7,"area":null},{"id":"2608.04205","title":"MatrAIx: Simulating the World with 8.3 Billion Persona Agents","created":"2026-08-04","cited_by_count":7,"area":"agents"},{"id":"2504.08820","title":"CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2510.09905","title":"The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2503.16094","title":"Cultural Alignment in Large Language Models Using Soft Prompt Tuning","created":"2025-03-20","cited_by_count":5,"area":"alignment"},{"id":"2601.08951","title":"PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2503.12613","title":"Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2505.11861","title":"Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity","created":"2025-05-17","cited_by_count":4,"area":"alignment"},{"id":"2505.13531","title":"AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2509.22888","title":"JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2602.12116","title":"P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling","created":"2026-02-12","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":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2412.16783","title":"SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs","created":"2024-12-21","cited_by_count":3,"area":null},{"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":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2410.17271","title":"Rules, Cases, and Reasoning: Positivist Legal Theory as a Framework for Pluralistic AI Alignment","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2501.10476","title":"Revisiting Rogers' Paradox in the Context of Human-AI Interaction","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2506.02431","title":"From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Models","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.12699","title":"Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2510.21180","title":"Social Simulations with Large Language Model Risk Utopian Illusion","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2510.27672","title":"Culture Cartography: Mapping the Landscape of Cultural Knowledge","created":"2025-10-31","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":"2603.05723","title":"Cultural Perspectives and Expectations for Generative AI: A Global Survey Approach","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2603.16120","title":"Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.19519","title":"Inducing Sustained Creativity and Diversity in Large Language Models","created":"2026-03-19","cited_by_count":2,"area":null},{"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":"2605.01642","title":"Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2605.24319","title":"Omissive Bias in Religious Representation: Benchmarking LLM Answers to Everyday Ethical Decision-making","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2606.13808","title":"The Culture Funnel: You Can't Align What isn't in the Data","created":"2026-06-11","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":"2410.02230","title":"Mitigating Downstream Model Risks via Model Provenance","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2503.16480","title":"Human Preferences for Constructive Interactions in Language Model Alignment","created":"2025-03-05","cited_by_count":1,"area":"alignment"},{"id":"2603.00078","title":"Alignment Is Not Enough: A Relational Framework for Moral Standing in Human-AI Interaction","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2603.15527","title":"Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph","created":"2026-03-16","cited_by_count":1,"area":"alignment"},{"id":"2604.03238","title":"RLHF May Not Reflect Genuine Preferences","created":"2026-01-31","cited_by_count":1,"area":"alignment"},{"id":"2604.03493","title":"Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.19190","title":"Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South","created":"2026-05-18","cited_by_count":1,"area":"safety"},{"id":"2605.27382","title":"The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs","created":"2026-04-10","cited_by_count":1,"area":"alignment"},{"id":"2606.18774","title":"RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.08034","title":"PLURAL: A Global Dataset for Value Alignment","created":"2026-07-09","cited_by_count":1,"area":"alignment"},{"id":"2607.16232","title":"From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.30052","title":"The Language of the Question Selects the Market: Query Language and Exit IP as Separable Factors in Commercial Recommendations from a Generative Search Interface","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2610.00968","title":"Structure-agnostic Causal Representation Learning","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2409.16849","title":"Exposing Assumptions in AI Benchmarks through Cognitive Modelling","created":"2024-09-25","cited_by_count":0,"area":null}],"next_cursor":"100"}