{"total":217,"rows":[{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870,"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":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2302.07736","title":"Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech","created":"2023-02-11","cited_by_count":166,"area":null},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98,"area":"safety"},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2304.10145","title":"Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks","created":"2023-04-20","cited_by_count":89,"area":null},{"id":"2306.14924","title":"LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding","created":"2023-06-23","cited_by_count":64,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"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":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57,"area":null},{"id":"2310.12860","title":"Probing LLMs for hate speech detection: strengths and vulnerabilities","created":"2023-10-19","cited_by_count":52,"area":null},{"id":"2311.17391","title":"Unveiling the Implicit Toxicity in Large Language Models","created":"2023-11-29","cited_by_count":51,"area":null},{"id":"2305.14965","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","created":"2023-05-24","cited_by_count":49,"area":"safety"},{"id":"2305.16171","title":"Multi-lingual and Multi-cultural Figurative Language Understanding","created":"2023-05-25","cited_by_count":47,"area":null},{"id":"2305.04446","title":"Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks","created":"2023-05-08","cited_by_count":46,"area":null},{"id":"2305.17680","title":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","created":"2023-05-28","cited_by_count":46,"area":null},{"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":"2210.10045","title":"SafeText: A Benchmark for Exploring Physical Safety in Language Models","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2305.17678","title":"Decoding the Underlying Meaning of Multimodal Hateful Memes","created":"2023-05-28","cited_by_count":39,"area":null},{"id":"2306.04746","title":"Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models","created":"2023-06-07","cited_by_count":39,"area":null},{"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":"2311.09090","title":"Social Bias Probing: Fairness Benchmarking for Language Models","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2204.02952","title":"Inducing Positive Perspectives with Text Reframing","created":"2022-04-06","cited_by_count":31,"area":null},{"id":"2311.00321","title":"HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2307.03214","title":"PREADD: Prefix-Adaptive Decoding for Controlled Text Generation","created":"2023-07-06","cited_by_count":29,"area":null},{"id":"2401.11839","title":"AI for social science and social science of AI: A Survey","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2312.11523","title":"ToViLaG: Your Visual-Language Generative Model is Also An Evildoer","created":"2023-12-13","cited_by_count":27,"area":null},{"id":"2305.17174","title":"From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models","created":"2023-05-26","cited_by_count":26,"area":null},{"id":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26,"area":null},{"id":"2209.04889","title":"Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech","created":"2022-09-11","cited_by_count":25,"area":null},{"id":"2402.11406","title":"Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection","created":"2024-02-18","cited_by_count":25,"area":null},{"id":"2301.09211","title":"An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models","created":"2023-01-22","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":"2406.05344","title":"MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention","created":"2024-06-08","cited_by_count":20,"area":"safety"},{"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":"2403.18152","title":"Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency","created":"2024-03-26","cited_by_count":18,"area":null},{"id":"2404.06138","title":"Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages","created":"2024-04-09","cited_by_count":18,"area":null},{"id":"2206.04007","title":"Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization","created":"2022-06-08","cited_by_count":17,"area":null},{"id":"2403.17368","title":"ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?","created":"2024-03-26","cited_by_count":17,"area":null},{"id":"2205.12495","title":"ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection","created":"2022-05-25","cited_by_count":15,"area":"lr"},{"id":"2403.02513","title":"Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF","created":"2024-03-04","cited_by_count":15,"area":"alignment"},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14,"area":null},{"id":"2309.14517","title":"Watch Your Language: Investigating Content Moderation with Large Language Models","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2311.09585","title":"LifeTox: Unveiling Implicit Toxicity in Life Advice","created":"2023-11-16","cited_by_count":14,"area":null},{"id":"2502.06207","title":"Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2502.11073","title":"Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions","created":"2025-02-16","cited_by_count":14,"area":"mllm"},{"id":"2403.10088","title":"Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF","created":"2024-03-15","cited_by_count":13,"area":"alignment"},{"id":"2405.02411","title":"The Call for Socially Aware Language Technologies","created":"2024-05-03","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":"2303.03387","title":"CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network","created":"2023-03-02","cited_by_count":12,"area":null},{"id":"2508.06570","title":"ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos","created":"2025-08-07","cited_by_count":12,"area":null},{"id":"2402.13022","title":"SoMeLVLM: A Large Vision Language Model for Social Media Processing","created":"2024-02-20","cited_by_count":11,"area":"mllm"},{"id":"2406.03953","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","cited_by_count":11,"area":null},{"id":"2609.24574","title":"Evaluating Decision Models for Text Annotation in Computational Social Science","created":"2026-09-21","cited_by_count":11,"area":null},{"id":"2312.04804","title":"Hate Cannot Drive out Hate: Forecasting Conversation Incivility following Replies to Hate Speech","created":"2023-12-08","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":"2405.01842","title":"SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2305.10547","title":"Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2408.04965","title":"Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks","created":"2024-08-09","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":"2210.16978","title":"XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models","created":"2022-10-30","cited_by_count":8,"area":null},{"id":"2305.16470","title":"Measuring the Effect of Influential Messages on Varying Personas","created":"2023-05-25","cited_by_count":8,"area":null},{"id":"2402.08225","title":"Improving Black-box Robustness with In-Context Rewriting","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2403.19836","title":"Target Span Detection for Implicit Harmful Content","created":"2024-03-28","cited_by_count":8,"area":"safety"},{"id":"2503.02776","title":"Implicit Bias in LLMs: A Survey","created":"2025-03-04","cited_by_count":8,"area":"safety"},{"id":"2208.07522","title":"Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wild","created":"2022-08-16","cited_by_count":7,"area":"safety"},{"id":"2306.01105","title":"Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2307.12418","title":"HateModerate: Testing Hate Speech Detectors against Content Moderation Policies","created":"2023-07-23","cited_by_count":7,"area":null},{"id":"2402.03221","title":"\"Define Your Terms\" : Enhancing Efficient Offensive Speech Classification with Definition","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2403.16685","title":"ToXCL: A Unified Framework for Toxic Speech Detection and Explanation","created":"2024-03-25","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":"2406.06840","title":"Silent Signals, Loud Impact: LLMs for Word-Sense Disambiguation of Coded Dog Whistles","created":"2024-06-10","cited_by_count":7,"area":null},{"id":"2407.15399","title":"Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models","created":"2024-07-22","cited_by_count":7,"area":"alignment"},{"id":"2410.05600","title":"Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2411.01844","title":"DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship","created":"2024-11-04","cited_by_count":7,"area":null},{"id":"2412.15035","title":"LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies","created":"2024-12-19","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":"2205.01374","title":"Hidden behind the obvious: misleading keywords and implicitly abusive language on social media","created":"2022-05-03","cited_by_count":6,"area":null},{"id":"2406.14023","title":"Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2407.04130","title":"Towards Automating Text Annotation: A Case Study on Semantic Proximity Annotation using GPT-4","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2410.00775","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","created":"2024-10-01","cited_by_count":6,"area":null},{"id":"2412.11704","title":"Adapting Chat Language Models Using Only Target Unlabeled Language Data","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2412.12072","title":"Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats","created":"2024-12-16","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":"2303.10311","title":"On the rise of fear speech in online social media","created":"2023-03-18","cited_by_count":5,"area":null},{"id":"2305.06545","title":"GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2310.15439","title":"K-HATERS: A Hate Speech Detection Corpus in Korean with Target-Specific Ratings","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2412.15268","title":"Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2503.07237","title":"LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2209.06317","title":"Quantitative AI Risk Assessments: Opportunities and Challenges","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2210.00910","title":"Hypothesis Engineering for Zero-Shot Hate Speech Detection","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2210.07595","title":"The State of Profanity Obfuscation in Natural Language Processing","created":"2022-10-14","cited_by_count":4,"area":null}],"next_cursor":"100"}