{"total":271,"rows":[{"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":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356,"area":null},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222,"area":"safety"},{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217,"area":null},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"area":null},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110,"area":null},{"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":"2305.01219","title":"Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models","created":"2023-05-02","cited_by_count":94,"area":"safety"},{"id":"2106.06361","title":"Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution","created":"2021-06-11","cited_by_count":89,"area":"safety"},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76,"area":null},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"area":null},{"id":"2102.13004","title":"Towards Unbiased and Accurate Deferral to Multiple Experts","created":"2021-02-25","cited_by_count":72,"area":null},{"id":"2109.13563","title":"Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement","created":"2021-09-28","cited_by_count":72,"area":null},{"id":"2305.17256","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","created":"2023-05-26","cited_by_count":69,"area":null},{"id":"2308.16149","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","created":"2023-08-30","cited_by_count":69,"area":null},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66,"area":"safety"},{"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":"2205.04274","title":"Detecting and Understanding Harmful Memes: A Survey","created":"2022-05-09","cited_by_count":58,"area":null},{"id":"2302.04863","title":"Knowledge is a Region in Weight Space for Fine-tuned Language Models","created":"2023-02-09","cited_by_count":58,"area":null},{"id":"2108.11830","title":"Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts","created":"2021-08-26","cited_by_count":56,"area":null},{"id":"2401.05949","title":"Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning","created":"2024-01-11","cited_by_count":53,"area":"safety"},{"id":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","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":"2101.06969","title":"Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks","created":"2021-01-18","cited_by_count":49,"area":null},{"id":"2109.09483","title":"ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI","created":"2021-09-20","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":"2309.06055","title":"Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review","created":"2023-09-12","cited_by_count":39,"area":"safety"},{"id":"2108.05927","title":"Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages","created":"2021-08-12","cited_by_count":38,"area":null},{"id":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36,"area":"safety"},{"id":"2205.12390","title":"Toxicity Detection with Generative Prompt-based Inference","created":"2022-05-24","cited_by_count":35,"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":"2103.00153","title":"Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go","created":"2021-02-27","cited_by_count":33,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2407.12824","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models","created":"2024-07-02","cited_by_count":32,"area":null},{"id":"2102.09665","title":"MUDES: Multilingual Detection of Offensive Spans","created":"2021-02-18","cited_by_count":30,"area":null},{"id":"2109.05074","title":"FBERT: A Neural Transformer for Identifying Offensive Content","created":"2021-09-10","cited_by_count":30,"area":null},{"id":"2109.03552","title":"Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathi","created":"2021-09-08","cited_by_count":28,"area":null},{"id":"2303.02242","title":"TrojText: Test-time Invisible Textual Trojan Insertion","created":"2023-03-03","cited_by_count":28,"area":null},{"id":"2307.01680","title":"Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation","created":"2023-07-04","cited_by_count":28,"area":null},{"id":"2106.00742","title":"A systematic review of Hate Speech automatic detection using Natural Language Processing","created":"2021-05-22","cited_by_count":27,"area":null},{"id":"2305.14910","title":"From Shortcuts to Triggers: Backdoor Defense with Denoised PoE","created":"2023-05-24","cited_by_count":27,"area":null},{"id":"2212.10529","title":"Evaluating Psychological Safety of Large Language Models","created":"2022-12-20","cited_by_count":26,"area":null},{"id":"2402.19334","title":"Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge","created":"2024-02-29","cited_by_count":26,"area":null},{"id":"2103.11528","title":"A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts","created":"2021-03-22","cited_by_count":25,"area":null},{"id":"2305.02394","title":"Defending against Insertion-based Textual Backdoor Attacks via Attribution","created":"2023-05-03","cited_by_count":25,"area":"safety"},{"id":"2206.01832","title":"Kallima: A Clean-label Framework for Textual Backdoor Attacks","created":"2022-06-03","cited_by_count":24,"area":"safety"},{"id":"2209.08207","title":"APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations","created":"2022-09-17","cited_by_count":23,"area":null},{"id":"2211.00107","title":"Where to start? Analyzing the potential value of intermediate models","created":"2022-10-31","cited_by_count":23,"area":null},{"id":"2105.05996","title":"Multilingual Offensive Language Identification for Low-resource Languages","created":"2021-05-12","cited_by_count":22,"area":null},{"id":"2112.07868","title":"Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases","created":"2021-12-15","cited_by_count":21,"area":null},{"id":"2305.11596","title":"Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation","created":"2023-05-19","cited_by_count":21,"area":null},{"id":"2106.04681","title":"Data Expansion using Back Translation and Paraphrasing for Hate Speech Detection","created":"2021-05-25","cited_by_count":20,"area":null},{"id":"2109.00227","title":"Dataset for Identification of Homophobia and Transophobia in Multilingual YouTube Comments","created":"2021-09-01","cited_by_count":20,"area":null},{"id":"2310.18633","title":"Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots","created":"2023-10-28","cited_by_count":19,"area":"safety"},{"id":"2106.09460","title":"DravidianCodeMix: Sentiment Analysis and Offensive Language Identification Dataset for Dravidian Languages in Code-Mixed Text","created":"2021-06-17","cited_by_count":18,"area":null},{"id":"2109.15144","title":"A Review of Text Style Transfer using Deep Learning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2202.06218","title":"Emotion Based Hate Speech Detection using Multimodal Learning","created":"2022-02-13","cited_by_count":18,"area":null},{"id":"2310.06458","title":"Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features","created":"2023-10-10","cited_by_count":18,"area":null},{"id":"2112.09301","title":"Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages","created":"2021-12-17","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":"2302.14003","title":"Systematic Rectification of Language Models via Dead-end Analysis","created":"2023-02-27","cited_by_count":16,"area":null},{"id":"2305.12675","title":"A Frustratingly Simple Decoding Method for Neural Text Generation","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2103.14972","title":"HateBR: A Large Expert Annotated Corpus of Brazilian Instagram Comments for Offensive Language and Hate Speech Detection","created":"2021-03-27","cited_by_count":15,"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":"2305.16503","title":"IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks","created":"2023-05-25","cited_by_count":15,"area":"safety"},{"id":"2105.14888","title":"An Exploratory Analysis of the Relation Between Offensive Language and Mental Health","created":"2021-05-31","cited_by_count":14,"area":null},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14,"area":null},{"id":"2205.14036","title":"StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypes","created":"2022-05-27","cited_by_count":14,"area":null},{"id":"2206.00372","title":"BD-SHS: A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts","created":"2022-06-01","cited_by_count":14,"area":null},{"id":"2302.09270","title":"Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements","created":"2023-02-18","cited_by_count":14,"area":null},{"id":"2311.18147","title":"DisCGen: A Framework for Discourse-Informed Counterspeech Generation","created":"2023-11-29","cited_by_count":14,"area":null},{"id":"2401.06526","title":"MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection","created":"2024-01-12","cited_by_count":14,"area":null},{"id":"2105.09052","title":"Methods for Detoxification of Texts for the Russian Language","created":"2021-05-19","cited_by_count":13,"area":null},{"id":"2107.04313","title":"Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset","created":"2021-07-09","cited_by_count":13,"area":null},{"id":"2301.10186","title":"ViHOS: Hate Speech Spans Detection for Vietnamese","created":"2023-01-24","cited_by_count":13,"area":null},{"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":"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":"2109.10255","title":"Multi-Task Learning with Sentiment, Emotion, and Target Detection to Recognize Hate Speech and Offensive Language","created":"2021-09-21","cited_by_count":12,"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":"2305.17013","title":"D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Bias","created":"2023-05-26","cited_by_count":12,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2311.15023","title":"Offensive Language Identification in Transliterated and Code-Mixed Bangla","created":"2023-11-25","cited_by_count":12,"area":null},{"id":"2210.10329","title":"Language Detoxification with Attribute-Discriminative Latent Space","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2501.08284","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","created":"2025-01-14","cited_by_count":11,"area":null},{"id":"2103.01328","title":"ToxCCIn: Toxic Content Classification with Interpretability","created":"2021-03-01","cited_by_count":10,"area":null},{"id":"2210.00465","title":"Assessing the impact of contextual information in hate speech detection","created":"2022-10-02","cited_by_count":10,"area":null},{"id":"2311.07879","title":"Toxicity Detection is NOT all you Need: Measuring the Gaps to Supporting Volunteer Content Moderators","created":"2023-11-14","cited_by_count":10,"area":null},{"id":"2402.15951","title":"DetoxLLM: A Framework for Detoxification with Explanations","created":"2024-02-25","cited_by_count":10,"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":"2103.00455","title":"NLP-CUET@DravidianLangTech-EACL2021: Offensive Language Detection from Multilingual Code-Mixed Text using Transformers","created":"2021-02-28","cited_by_count":9,"area":null},{"id":"2310.14757","title":"SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"area":null},{"id":"2501.15438","title":"Cross-Modal Transfer from Memes to Videos: Addressing Data Scarcity in Hateful Video Detection","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2202.05690","title":"HaT5: Hate Language Identification using Text-to-Text Transfer Transformer","created":"2022-02-11","cited_by_count":8,"area":null},{"id":"2203.11331","title":"On The Robustness of Offensive Language Classifiers","created":"2022-03-21","cited_by_count":8,"area":null}],"next_cursor":"100"}