{"total":143,"rows":[{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139,"area":null},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87,"area":"alignment"},{"id":"2309.07034","title":"Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting","created":"2023-09-13","cited_by_count":81,"area":null},{"id":"2311.08370","title":"SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models","created":"2023-11-14","cited_by_count":76,"area":null},{"id":"2406.11580","title":"Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation","created":"2024-06-17","cited_by_count":62,"area":null},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"area":null},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2301.05036","title":"Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information","created":"2023-01-12","cited_by_count":52,"area":null},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51,"area":null},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2306.11559","title":"The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics","created":"2023-06-20","cited_by_count":46,"area":null},{"id":"2403.01931","title":"VariErr NLI: Separating Annotation Error from Human Label Variation","created":"2024-03-04","cited_by_count":42,"area":null},{"id":"2410.21306","title":"Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges","created":"2024-10-25","cited_by_count":42,"area":null},{"id":"2405.05860","title":"The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels","created":"2024-05-09","cited_by_count":38,"area":null},{"id":"2212.10543","title":"Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts","created":"2022-12-20","cited_by_count":36,"area":null},{"id":"2412.13091","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","created":"2024-12-17","cited_by_count":33,"area":null},{"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":"2405.01299","title":"The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation","created":"2024-05-02","cited_by_count":29,"area":null},{"id":"2403.01222","title":"Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions","created":"2024-03-02","cited_by_count":27,"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":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25,"area":null},{"id":"2311.00161","title":"Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language","created":"2023-10-31","cited_by_count":24,"area":null},{"id":"2301.10684","title":"Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreement","created":"2023-01-25","cited_by_count":23,"area":null},{"id":"2305.08414","title":"What's the Meaning of Superhuman Performance in Today's NLU?","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2308.01681","title":"NBIAS: A Natural Language Processing Framework for Bias Identification in Text","created":"2023-08-03","cited_by_count":23,"area":null},{"id":"2406.14462","title":"Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas","created":"2024-06-20","cited_by_count":23,"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":"2402.10723","title":"Conformalized Credal Set Predictors","created":"2024-02-16","cited_by_count":21,"area":null},{"id":"2410.11745","title":"Personas with Attitudes: Controlling LLMs for Diverse Data Annotation","created":"2024-10-15","cited_by_count":21,"area":null},{"id":"2402.11886","title":"The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth","created":"2024-02-19","cited_by_count":20,"area":null},{"id":"2305.16051","title":"What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns","created":"2023-05-25","cited_by_count":19,"area":null},{"id":"2206.15455","title":"Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions","created":"2022-06-30","cited_by_count":18,"area":null},{"id":"2311.05265","title":"Don't Waste a Single Annotation: Improving Single-Label Classifiers Through Soft Labels","created":"2023-11-09","cited_by_count":17,"area":null},{"id":"2310.17428","title":"''Fifty Shades of Bias'': Normative Ratings of Gender Bias in GPT Generated English Text","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2402.16102","title":"Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?","created":"2024-02-25","cited_by_count":15,"area":null},{"id":"2407.03974","title":"LLM Roleplay: Simulating Human-Chatbot Interaction","created":"2024-07-04","cited_by_count":15,"area":null},{"id":"2305.14246","title":"Modeling Empathic Similarity in Personal Narratives","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2403.19559","title":"Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset","created":"2024-03-28","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":"2411.15462","title":"HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter","created":"2024-11-23","cited_by_count":13,"area":null},{"id":"2212.10405","title":"AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2402.06041","title":"A Prompt Response to the Demand for Automatic Gender-Neutral Translation","created":"2024-02-08","cited_by_count":12,"area":null},{"id":"2210.02659","title":"Explainable Abuse Detection as Intent Classification and Slot Filling","created":"2022-10-06","cited_by_count":11,"area":null},{"id":"2310.15398","title":"\"One-Size-Fits-All\"? Examining Expectations around What Constitute \"Fair\" or \"Good\" NLG System Behaviors","created":"2023-10-23","cited_by_count":11,"area":null},{"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":"2407.18078","title":"PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization","created":"2024-07-25","cited_by_count":11,"area":null},{"id":"2403.19260","title":"NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2403.02268","title":"Subjective $\\textit{Isms}$? On the Danger of Conflating Hate and Offence in Abusive Language Detection","created":"2024-03-04","cited_by_count":9,"area":null},{"id":"2407.14259","title":"Voices in a Crowd: Searching for Clusters of Unique Perspectives","created":"2024-07-19","cited_by_count":9,"area":null},{"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":"2404.02340","title":"Corpus Considerations for Annotator Modeling and Scaling","created":"2024-04-02","cited_by_count":8,"area":null},{"id":"2210.04573","title":"HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2305.13589","title":"BiasX: \"Thinking Slow\" in Toxic Content Moderation with Explanations of Implied Social Biases","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2307.02191","title":"Evaluating AI systems under uncertain ground truth: a case study in dermatology","created":"2023-07-05","cited_by_count":7,"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":"2406.04106","title":"Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2410.15911","title":"DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2410.23448","title":"Venire: A Machine Learning-Guided Panel Review System for Community Content Moderation","created":"2024-10-30","cited_by_count":7,"area":null},{"id":"2506.18576","title":"A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification Performance","created":"2025-06-23","cited_by_count":7,"area":"safety"},{"id":"2305.18034","title":"A Corpus for Sentence-level Subjectivity Detection on English News Articles","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2307.12973","title":"Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation","created":"2023-07-24","cited_by_count":6,"area":null},{"id":"2308.10592","title":"BAN-PL: a Novel Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2409.12218","title":"ARTICLE: Annotator Reliability Through In-Context Learning","created":"2024-09-18","cited_by_count":6,"area":null},{"id":"2411.07417","title":"Untangling Hate Speech Definitions: A Semantic Componential Analysis Across Cultures and Domains","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2505.12727","title":"What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2505.20033","title":"EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2506.20844","title":"The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers","created":"2025-06-25","cited_by_count":6,"area":null},{"id":"2311.03153","title":"Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It's Best to Relate Perspectives!","created":"2023-11-06","cited_by_count":5,"area":null},{"id":"2208.04104","title":"INSPIRED2: An Improved Dataset for Sociable Conversational Recommendation","created":"2022-08-08","cited_by_count":4,"area":null},{"id":"2208.08758","title":"Understanding Interpersonal Conflict Types and their Impact on Perception Classification","created":"2022-08-18","cited_by_count":4,"area":null},{"id":"2306.09918","title":"No Strong Feelings One Way or Another: Re-operationalizing Neutrality in Natural Language Inference","created":"2023-06-16","cited_by_count":4,"area":"lr"},{"id":"2406.08080","title":"AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2506.07297","title":"Subjectivity in the Annotation of Bridging Anaphora","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2507.02593","title":"Revisiting Active Learning under (Human) Label Variation","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2511.05613","title":"Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations","created":"2025-11-06","cited_by_count":4,"area":null},{"id":"2601.11459","title":"Interactive Narrative Analytics: Bridging Computational Narrative Extraction and Human Sensemaking","created":"2026-01-16","cited_by_count":4,"area":null},{"id":"2201.06674","title":"TYPIC: A Corpus of Template-Based Diagnostic Comments on Argumentation","created":"2022-01-18","cited_by_count":3,"area":null},{"id":"2311.09443","title":"Subtle Misogyny Detection and Mitigation: An Expert-Annotated Dataset","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2403.00418","title":"LLMs for Targeted Sentiment in News Headlines: Exploring the Descriptive-Prescriptive Dilemma","created":"2024-03-01","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":"2501.09265","title":"Perspective Transition of Large Language Models for Solving Subjective Tasks","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2502.08266","title":"Dealing with Annotator Disagreement in Hate Speech Classification","created":"2025-02-12","cited_by_count":3,"area":"safety"},{"id":"2502.11959","title":"STRIVE: Structured Reasoning for Self-Improvement in Claim Verification","created":"2025-02-17","cited_by_count":3,"area":"lr"},{"id":"2508.17164","title":"The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum","created":"2025-08-23","cited_by_count":3,"area":null},{"id":"2509.06704","title":"Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments","created":"2025-09-08","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":"2302.02064","title":"Lived Experience Matters: Automatic Detection of Stigma on Social Media Toward People Who Use Substances","created":"2023-02-04","cited_by_count":2,"area":null},{"id":"2307.10749","title":"Mitigating Voter Attribute Bias for Fair Opinion Aggregation","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2309.11896","title":"Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2402.10424","title":"Pelican Soup Framework: A Theoretical Framework for Language Model Capabilities","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2409.20204","title":"Divided by discipline? A systematic literature review on the quantification of online sexism and misogyny using a semi-automated approach","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2505.13418","title":"Dementia Through Different Eyes: Explainable Modeling of Human and LLM Perceptions for Early Awareness","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2505.20088","title":"Multi-Domain Explainability of Preferences","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2508.11122","title":"+VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checking","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2404.09615","title":"If there's a Trigger Warning, then where's the Trigger? Investigating Trigger Warnings at the Passage Level","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2407.01158","title":"Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":1,"area":"rag"},{"id":"2410.19812","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2411.08752","title":"Multi-Perspective Stance Detection","created":"2024-11-13","cited_by_count":1,"area":null},{"id":"2412.04025","title":"Exploring the Influence of Label Aggregation on Minority Voices: Implications for Dataset Bias and Model Training","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2504.01902","title":"Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights","created":"2025-04-02","cited_by_count":1,"area":null}],"next_cursor":"100"}