{"total":86,"rows":[{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83,"area":"safety"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"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":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"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":"2502.20897","title":"Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions","created":"2025-02-28","cited_by_count":33,"area":null},{"id":"2410.03775","title":"Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge","created":"2024-10-03","cited_by_count":31,"area":null},{"id":"2311.09743","title":"Capturing Perspectives of Crowdsourced Annotators in Subjective Learning Tasks","created":"2023-11-16","cited_by_count":29,"area":null},{"id":"2503.15484","title":"Value Profiles for Encoding Human Variation","created":"2025-03-19","cited_by_count":29,"area":"alignment"},{"id":"2406.11852","title":"Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2311.09799","title":"How Far Can We Extract Diverse Perspectives from Large Language Models?","created":"2023-11-16","cited_by_count":22,"area":null},{"id":"2501.19047","title":"Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)","created":"2025-01-31","cited_by_count":20,"area":null},{"id":"2404.14068","title":"Holistic Safety and Responsibility Evaluations of Advanced AI Models","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2404.15720","title":"Annotator-Centric Active Learning for Subjective NLP Tasks","created":"2024-04-24","cited_by_count":18,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2404.17047","title":"Near to Mid-term Risks and Opportunities of Open-Source Generative AI","created":"2024-04-25","cited_by_count":13,"area":null},{"id":"2405.08597","title":"Risks and Opportunities of Open-Source Generative AI","created":"2024-05-14","cited_by_count":13,"area":null},{"id":"2406.11757","title":"STAR: SocioTechnical Approach to Red Teaming Language Models","created":"2024-06-17","cited_by_count":13,"area":"safety"},{"id":"2404.10857","title":"D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation","created":"2024-04-16","cited_by_count":11,"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":"2502.14019","title":"Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems","created":"2025-02-19","cited_by_count":11,"area":null},{"id":"2507.13383","title":"Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models","created":"2025-07-15","cited_by_count":11,"area":"alignment"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2403.06009","title":"Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations","created":"2024-03-09","cited_by_count":10,"area":null},{"id":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","cited_by_count":10,"area":"alignment"},{"id":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2508.02853","title":"Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives","created":"2025-08-04","cited_by_count":10,"area":"moe"},{"id":"2511.14476","title":"Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior","created":"2025-11-18","cited_by_count":9,"area":"alignment"},{"id":"2402.06811","title":"Discipline and Label: A WEIRD Genealogy and Social Theory of Data Annotation","created":"2024-02-09","cited_by_count":8,"area":null},{"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":"2310.02457","title":"The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising \"Alignment\" in Large Language Models","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2407.16883","title":"A Standardized Machine-readable Dataset Documentation Format for Responsible AI","created":"2024-06-04","cited_by_count":7,"area":null},{"id":"2406.05902","title":"Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human Feedback","created":"2024-06-09","cited_by_count":6,"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":"2312.06024","title":"Thinking Assistants: LLM-Based Conversational Assistants that Help Users Think By Asking rather than Answering","created":"2023-12-10","cited_by_count":4,"area":"lr"},{"id":"2410.17032","title":"Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2406.14903","title":"GIEBench: Towards Holistic Evaluation of Group Identity-based Empathy for Large Language Models","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2510.12817","title":"From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2602.08716","title":"PERSPECTRA: A Scalable and Configurable Pluralist Benchmark of Perspectives from Arguments","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2412.18551","title":"Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2505.16220","title":"Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2507.05980","title":"Lost in Localization: Building RabakBench with Human-in-the-Loop Validation to Measure Multilingual Safety Gaps","created":"2025-07-08","cited_by_count":2,"area":"safety"},{"id":"2601.18061","title":"Expert Evaluation and the Limits of Human Feedback in Mental Health AI Safety Testing","created":"2026-01-26","cited_by_count":2,"area":"alignment"},{"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":"2602.19458","title":"ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2603.01211","title":"A Unified Framework to Quantify Cultural Intelligence of AI","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2604.23099","title":"ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation","created":"2026-04-25","cited_by_count":2,"area":null},{"id":"2503.04141","title":"HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMs","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2510.00174","title":"PrimeX: A Dataset of Worldview, Opinion, and Explanation","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.07105","title":"Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning","created":"2025-10-08","cited_by_count":1,"area":null},{"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":"2601.06631","title":"Labels have Human Values: Value Calibration of Subjective Tasks","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2601.13669","title":"CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks","created":"2026-01-20","cited_by_count":1,"area":"alignment"},{"id":"2602.07376","title":"Do Large Language Models Reflect Demographic Pluralism in Safety?","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2604.17968","title":"From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives?","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2507.16033","title":"\"Just a strange pic\": Evaluating 'safety' in GenAI Image safety annotation tasks from diverse annotators' perspectives","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2507.17922","title":"From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models","created":"2025-07-23","cited_by_count":0,"area":"safety"},{"id":"2509.08217","title":"Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2602.06055","title":"Are we chasing ghosts? Quantifying unattributable polarization, and attributing the rest to annotator groups","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.08425","title":"Learning Who Disagrees: Demographic Importance Weighting for Modeling Annotator Distributions with DiADEM","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.17301","title":"RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2604.20805","title":"Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.05329","title":"Understanding Annotator Safety Policy with Interpretability","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.13801","title":"Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.18648","title":"An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.26947","title":"KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.27914","title":"Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm","created":"2026-05-27","cited_by_count":0,"area":"synth"},{"id":"2605.29797","title":"Metric-Dependent Annotation Saturation for Learning from Label Distributions","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.09408","title":"Can Data Work be Reparative?","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.12552","title":"Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.28772","title":"Majority Vote Silences Minority Values: Annotator Disagreement at the Hate/Offensive Boundary in HateXplain","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.09262","title":"Geopolitical alignment: Endorsement effects in large language models","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2608.01458","title":"PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs","created":"2026-08-02","cited_by_count":0,"area":"alignment"},{"id":"2608.21567","title":"Quantifying geographic domain shift to decouple the geospatial transferability of human mobility flow generation models","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.30842","title":"Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.00222","title":"LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00250","title":"CompanionSim: Synthetic Data for Evaluating Anthropomorphism in Human-AI Relationships","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.32267","title":"When Can Old Evaluations Certify a New Model? Label-Efficient Release Decisions under Evaluator Drift","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}