{"total":264,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773,"area":null},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422,"area":null},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"area":null},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169,"area":null},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"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":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126,"area":null},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109,"area":"agents"},{"id":"2401.06730","title":"Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty","created":"2024-01-12","cited_by_count":106,"area":null},{"id":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100,"area":"synth"},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","cited_by_count":92,"area":null},{"id":"2305.06626","title":"When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks","created":"2023-05-11","cited_by_count":90,"area":null},{"id":"2309.07034","title":"Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting","created":"2023-09-13","cited_by_count":81,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2405.16455","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","created":"2024-05-26","cited_by_count":72,"area":"alignment"},{"id":"2203.13299","title":"Mix and Match: Learning-free Controllable Text Generation using Energy Language Models","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2404.01030","title":"Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation","created":"2024-04-01","cited_by_count":66,"area":null},{"id":"2212.08620","title":"POTATO: The Portable Text Annotation Tool","created":"2022-12-16","cited_by_count":64,"area":null},{"id":"2209.03942","title":"Data Feedback Loops: Model-driven Amplification of Dataset Biases","created":"2022-09-08","cited_by_count":60,"area":null},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55,"area":"alignment"},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54,"area":null},{"id":"2201.10474","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","created":"2022-01-25","cited_by_count":53,"area":null},{"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":"2306.06826","title":"When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset","created":"2023-06-12","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":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49,"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":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"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":"2304.10619","title":"\"HOT\" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media","created":"2023-04-20","cited_by_count":45,"area":"safety"},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45,"area":null},{"id":"2204.14256","title":"Handling and Presenting Harmful Text in NLP Research","created":"2022-04-29","cited_by_count":43,"area":null},{"id":"2305.14663","title":"You Are What You Annotate: Towards Better Models through Annotator Representations","created":"2023-05-24","cited_by_count":40,"area":null},{"id":"2601.17087","title":"Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations","created":"2026-01-23","cited_by_count":40,"area":"agents"},{"id":"2202.08011","title":"Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks","created":"2022-02-16","cited_by_count":36,"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":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","cited_by_count":36,"area":null},{"id":"2308.15399","title":"Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?","created":"2023-08-29","cited_by_count":36,"area":"lr"},{"id":"2306.01985","title":"COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements","created":"2023-06-03","cited_by_count":34,"area":null},{"id":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","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":"2410.07991","title":"Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets","created":"2024-10-10","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":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"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":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"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":"2210.10839","title":"How Hate Speech Varies by Target Identity: A Computational Analysis","created":"2022-10-19","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":"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":"2210.14531","title":"Unifying Data Perspectivism and Personalization: An Application to Social Norms","created":"2022-10-26","cited_by_count":22,"area":null},{"id":"2303.17927","title":"Cross-Cultural Transfer Learning for Chinese Offensive Language Detection","created":"2023-03-31","cited_by_count":21,"area":null},{"id":"2407.02099","title":"Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior","created":"2024-07-02","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":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2502.12858","title":"Rejected Dialects: Biases Against African American Language in Reward Models","created":"2025-02-18","cited_by_count":20,"area":"alignment"},{"id":"2305.02364","title":"PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narratives","created":"2023-05-03","cited_by_count":19,"area":null},{"id":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","cited_by_count":18,"area":null},{"id":"2206.01532","title":"Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization","created":"2022-06-03","cited_by_count":17,"area":"lr"},{"id":"2307.04761","title":"Understanding Counterspeech for Online Harm Mitigation","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2310.14979","title":"ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variation","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2403.13213","title":"From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards","created":"2024-03-20","cited_by_count":17,"area":null},{"id":"2301.12534","title":"Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive","created":"2023-01-29","cited_by_count":16,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"area":null},{"id":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2311.05074","title":"GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives","created":"2023-11-09","cited_by_count":16,"area":"safety"},{"id":"2507.13541","title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","created":"2025-07-17","cited_by_count":16,"area":null},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14,"area":null},{"id":"2310.11878","title":"From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification","created":"2023-10-18","cited_by_count":14,"area":null},{"id":"2210.09306","title":"Mitigating Covertly Unsafe Text within Natural Language Systems","created":"2022-10-17","cited_by_count":13,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2601.09065","title":"Beyond Consensus: Perspectivist Modeling and Evaluation of Annotator Disagreement in NLP","created":"2026-01-14","cited_by_count":13,"area":null},{"id":"2112.07475","title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks","created":"2021-12-14","cited_by_count":12,"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":"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":"2204.06251","title":"Experimental Standards for Deep Learning in Natural Language Processing Research","created":"2022-04-13","cited_by_count":10,"area":null},{"id":"2403.04085","title":"Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations","created":"2024-03-06","cited_by_count":10,"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":"2410.03448","title":"\"Cold, Calculated, and Condescending\": How AI Identifies and Explains Ableism Compared to Disabled People","created":"2024-10-04","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":"2603.05912","title":"DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality","created":"2026-03-06","cited_by_count":10,"area":"agents"},{"id":"2306.00198","title":"An Invariant Learning Characterization of Controlled Text Generation","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2311.07115","title":"Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions","created":"2023-11-13","cited_by_count":9,"area":null},{"id":"2402.07214","title":"Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification","created":"2024-02-11","cited_by_count":9,"area":null},{"id":"2205.07233","title":"Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy","created":"2022-05-15","cited_by_count":8,"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":"2402.12431","title":"Understanding Fine-grained Distortions in Reports of Scientific Findings","created":"2024-02-19","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}],"next_cursor":"100"}