{"total":171,"rows":[{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355,"area":"diffusion"},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"area":null},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536,"area":"safety"},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2406.13352","title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","created":"2024-06-19","cited_by_count":145,"area":"agents"},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114,"area":null},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106,"area":null},{"id":"2401.05654","title":"Towards Conversational Diagnostic AI","created":"2024-01-11","cited_by_count":79,"area":null},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73,"area":null},{"id":"2305.11840","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","created":"2023-05-19","cited_by_count":66,"area":null},{"id":"2307.13692","title":"ARB: Advanced Reasoning Benchmark for Large Language Models","created":"2023-07-25","cited_by_count":60,"area":"lr"},{"id":"2206.08931","title":"CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation","created":"2022-06-09","cited_by_count":59,"area":null},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51,"area":null},{"id":"2407.14933","title":"Consent in Crisis: The Rapid Decline of the AI Data Commons","created":"2024-07-20","cited_by_count":46,"area":null},{"id":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","cited_by_count":43,"area":"synth"},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2304.14749","title":"Understanding accountability in algorithmic supply chains","created":"2023-04-28","cited_by_count":40,"area":null},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2406.14325","title":"Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers","created":"2024-06-20","cited_by_count":34,"area":null},{"id":"2302.00799","title":"Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI","created":"2023-02-01","cited_by_count":33,"area":null},{"id":"2401.13822","title":"Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on Hugging Face","created":"2024-01-24","cited_by_count":27,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2311.05800","title":"Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval","created":"2023-11-10","cited_by_count":24,"area":null},{"id":"2305.09073","title":"Consensus and Subjectivity of Skin Tone Annotation for ML Fairness","created":"2023-05-16","cited_by_count":22,"area":null},{"id":"2506.09956","title":"LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge","created":"2025-06-11","cited_by_count":21,"area":"safety"},{"id":"2406.07954","title":"Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition","created":"2024-06-12","cited_by_count":20,"area":null},{"id":"2306.09562","title":"Reproducibility in NLP: What Have We Learned from the Checklist?","created":"2023-06-16","cited_by_count":18,"area":null},{"id":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2304.10655","title":"The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions","created":"2023-04-20","cited_by_count":17,"area":null},{"id":"2306.13701","title":"Use case cards: a use case reporting framework inspired by the European AI Act","created":"2023-06-23","cited_by_count":15,"area":null},{"id":"2404.12691","title":"Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?","created":"2024-04-19","cited_by_count":15,"area":null},{"id":"2410.04772","title":"From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2402.13635","title":"The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2207.02848","title":"A domain-specific language for describing machine learning datasets","created":"2022-07-05","cited_by_count":12,"area":null},{"id":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2307.16526","title":"No Fair Lunch: A Causal Perspective on Dataset Bias in Machine Learning for Medical Imaging","created":"2023-07-31","cited_by_count":11,"area":null},{"id":"2402.05160","title":"What's documented in AI? Systematic Analysis of 32K AI Model Cards","created":"2024-02-07","cited_by_count":11,"area":null},{"id":"2411.11937","title":"Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets","created":"2024-11-18","cited_by_count":11,"area":"alignment"},{"id":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"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":"2410.12974","title":"BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks","created":"2024-10-16","cited_by_count":10,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2405.06258","title":"Automatic Generation of Model and Data Cards: A Step Towards Responsible AI","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2512.04062","title":"Eval Factsheets: A Structured Framework for Documenting AI Evaluations","created":"2025-12-03","cited_by_count":9,"area":null},{"id":"2208.00932","title":"Masader Plus: A New Interface for Exploring +500 Arabic NLP Datasets","created":"2022-08-01","cited_by_count":8,"area":null},{"id":"2402.14880","title":"Automatic Histograms: Leveraging Language Models for Text Dataset Exploration","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2301.05154","title":"Mephisto: A Framework for Portable, Reproducible, and Iterative Crowdsourcing","created":"2023-01-12","cited_by_count":7,"area":null},{"id":"2312.06153","title":"Open Datasheets: Machine-readable Documentation for Open Datasets and Responsible AI Assessments","created":"2023-12-11","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":"2506.14652","title":"Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2302.05284","title":"A Systematic Literature Review of Human-Centered, Ethical, and Responsible AI","created":"2023-02-10","cited_by_count":6,"area":null},{"id":"2307.11525","title":"Model Reporting for Certifiable AI: A Proposal from Merging EU Regulation into AI Development","created":"2023-07-21","cited_by_count":6,"area":null},{"id":"2402.06353","title":"Copycats: the many lives of a publicly available medical imaging dataset","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2406.10366","title":"Improving the Validity and Practical Usefulness of AI/ML Evaluations Using an Estimands Framework","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2412.16089","title":"The Evolution of LLM Adoption in Industry Data Curation Practices","created":"2024-12-20","cited_by_count":6,"area":null},{"id":"2308.12885","title":"Collect, Measure, Repeat: Reliability Factors for Responsible AI Data Collection","created":"2023-08-22","cited_by_count":5,"area":null},{"id":"2311.05792","title":"Is a Seat at the Table Enough? Engaging Teachers and Students in Dataset Specification for ML in Education","created":"2023-11-09","cited_by_count":5,"area":null},{"id":"2404.06717","title":"Racial/Ethnic Categories in AI and Algorithmic Fairness: Why They Matter and What They Represent","created":"2024-04-10","cited_by_count":5,"area":null},{"id":"2410.05057","title":"SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2606.02915","title":"Any2Poster: Any-Source Poster Generation Across Modalities and Domains","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2608.10915","title":"ComBodied Agents: a New Paradigm of Human-Centric Agentic AI","created":"2026-08-11","cited_by_count":5,"area":"agents"},{"id":"2212.07877","title":"Manifestations of Xenophobia in AI Systems","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2311.03663","title":"Principles from Clinical Research for NLP Model Generalization","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2505.22778","title":"Machine Learning Models Have a Supply Chain Problem","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2510.24383","title":"Policy Cards: Machine-Readable Runtime Governance for Autonomous AI Agents","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2311.17259","title":"SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2406.04116","title":"Promoting the Responsible Development of Speech Datasets for Mental Health and Neurological Disorders Research","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2407.21028","title":"Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2504.04243","title":"Perils of Label Indeterminacy: A Case Study on Prediction of Neurological Recovery After Cardiac Arrest","created":"2025-04-05","cited_by_count":3,"area":null},{"id":"2508.08804","title":"TechOps: Technical Documentation Templates for the AI Act","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2603.13793","title":"GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languages","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2211.05485","title":"Understanding Text Classification Data and Models Using Aggregated Input Salience","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2306.12609","title":"Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2405.01590","title":"101 Billion Arabic Words Dataset","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2405.20643","title":"Learning Gaze-aware Compositional GAN","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2406.03245","title":"Reconfiguring Participatory Design to Resist AI Realism","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2406.06407","title":"A Taxonomy of Challenges to Curating Fair Datasets","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2408.02379","title":"The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2409.17216","title":"Data-Centric AI Governance: Addressing the Limitations of Model-Focused Policies","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2411.15626","title":"Aligning Generalisation Between Humans and Machines","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2502.13268","title":"Talking About the Assumption in the Room","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2505.08064","title":"Justified Evidence Collection for Argument-based AI Fairness Assurance","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2507.08866","title":"Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond","created":"2025-07-09","cited_by_count":2,"area":null},{"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":"2605.28158","title":"OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"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":"2607.26694","title":"Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2209.09666","title":"Documenting use cases in the affective computing domain using Unified Modeling Language","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2305.12829","title":"On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2310.10955","title":"A State-Vector Framework for Dataset Effects","created":"2023-10-17","cited_by_count":1,"area":null}],"next_cursor":"100"}