{"total":102,"rows":[{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2211.03759","title":"Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale","created":"2022-11-07","cited_by_count":262,"area":null},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158,"area":"safety"},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2201.01389","title":"Semantic Communications: Principles and Challenges","created":"2021-12-30","cited_by_count":91,"area":null},{"id":"2202.13047","title":"AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation","created":"2022-02-26","cited_by_count":79,"area":null},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2107.13541","title":"Towards Robustness Against Natural Language Word Substitutions","created":"2021-07-28","cited_by_count":69,"area":null},{"id":"2406.06007","title":"CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models","created":"2024-06-10","cited_by_count":64,"area":"mllm"},{"id":"2305.09941","title":"\"I'm fully who I am\": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation","created":"2023-05-17","cited_by_count":56,"area":null},{"id":"2112.11668","title":"How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?","created":"2021-12-22","cited_by_count":49,"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":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2405.20413","title":"Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters","created":"2024-05-30","cited_by_count":42,"area":"safety"},{"id":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"area":null},{"id":"2403.17661","title":"Language Models for Text Classification: Is In-Context Learning Enough?","created":"2024-03-26","cited_by_count":40,"area":null},{"id":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"area":null},{"id":"2311.05915","title":"Fake Alignment: Are LLMs Really Aligned Well?","created":"2023-11-10","cited_by_count":39,"area":null},{"id":"2202.04800","title":"The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning","created":"2022-02-10","cited_by_count":38,"area":"lr"},{"id":"2311.06899","title":"Flames: Benchmarking Value Alignment of LLMs in Chinese","created":"2023-11-12","cited_by_count":37,"area":"alignment"},{"id":"2209.03463","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","created":"2022-09-07","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":"2104.06999","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","created":"2021-04-14","cited_by_count":31,"area":null},{"id":"2308.11804","title":"Adversarial Illusions in Multi-Modal Embeddings","created":"2023-08-22","cited_by_count":29,"area":null},{"id":"2205.12331","title":"Certified Robustness Against Natural Language Attacks by Causal Intervention","created":"2022-05-24","cited_by_count":24,"area":null},{"id":"2203.00130","title":"Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2309.17415","title":"Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts","created":"2023-09-29","cited_by_count":23,"area":"rag"},{"id":"2311.11123","title":"(Why) Is My Prompt Getting Worse? Rethinking Regression Testing for Evolving LLM APIs","created":"2023-11-18","cited_by_count":23,"area":"lr"},{"id":"2109.02229","title":"Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack","created":"2021-09-06","cited_by_count":17,"area":null},{"id":"2310.00322","title":"Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games","created":"2023-09-30","cited_by_count":17,"area":"agents"},{"id":"2510.21189","title":"Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency","created":"2025-10-24","cited_by_count":17,"area":"safety"},{"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":"2111.09064","title":"Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification","created":"2021-11-17","cited_by_count":14,"area":null},{"id":"2404.08690","title":"Towards Building a Robust Toxicity Predictor","created":"2024-04-09","cited_by_count":14,"area":null},{"id":"2501.16750","title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2104.05996","title":"Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack","created":"2021-04-13","cited_by_count":13,"area":null},{"id":"2501.08203","title":"ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving","created":"2025-01-14","cited_by_count":13,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"area":null},{"id":"2103.01616","title":"Interpretable Multi-Modal Hate Speech Detection","created":"2021-03-02","cited_by_count":10,"area":null},{"id":"2503.19134","title":"MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks","created":"2025-03-24","cited_by_count":10,"area":"lr"},{"id":"2112.08321","title":"Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics","created":"2021-12-15","cited_by_count":9,"area":null},{"id":"2302.02568","title":"Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend","created":"2023-02-06","cited_by_count":9,"area":null},{"id":"2202.13056","title":"Automated Identification of Toxic Code Reviews Using ToxiCR","created":"2022-02-26","cited_by_count":8,"area":null},{"id":"2105.09985","title":"Measuring Model Fairness under Noisy Covariates: A Theoretical Perspective","created":"2021-05-20","cited_by_count":7,"area":null},{"id":"2102.04427","title":"RECAST: Enabling User Recourse and Interpretability of Toxicity Detection Models with Interactive Visualization","created":"2021-02-08","cited_by_count":6,"area":null},{"id":"2301.01874","title":"Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI","created":"2023-01-05","cited_by_count":6,"area":null},{"id":"2311.11796","title":"Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems","created":"2023-11-20","cited_by_count":6,"area":"safety"},{"id":"2201.06384","title":"Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2306.07033","title":"When Vision Fails: Text Attacks Against ViT and OCR","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2409.12739","title":"Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models","created":"2024-09-19","cited_by_count":5,"area":null},{"id":"2102.04895","title":"Leveraging cross-platform data to improve automated hate speech detection","created":"2021-02-09","cited_by_count":4,"area":null},{"id":"2110.13980","title":"Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2310.04465","title":"How toxic is antisemitism? Potentials and limitations of automated toxicity scoring for antisemitic online content","created":"2023-10-05","cited_by_count":4,"area":null},{"id":"2401.12720","title":"A Comprehensive View of the Biases of Toxicity and Sentiment Analysis Methods Towards Utterances with African American English Expressions","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2407.05977","title":"Exploring Human-LLM Conversations: Mental Models and the Originator of Toxicity","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2410.12621","title":"Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning","created":"2024-10-16","cited_by_count":4,"area":"lr"},{"id":"2107.06400","title":"Using BERT Encoding to Tackle the Mad-lib Attack in SMS Spam Detection","created":"2021-07-13","cited_by_count":3,"area":null},{"id":"2201.06093","title":"Adversarial Machine Learning Threat Analysis and Remediation in Open Radio Access Network (O-RAN)","created":"2022-01-16","cited_by_count":3,"area":null},{"id":"2212.02108","title":"Human-in-the-Loop Hate Speech Classification in a Multilingual Context","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2311.09428","title":"Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2312.07228","title":"Toxic language detection: a systematic review of Arabic datasets","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2501.01256","title":"Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2501.16836","title":"Misspellings in Natural Language Processing: A survey","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2601.06366","title":"SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use","created":"2026-01-10","cited_by_count":3,"area":null},{"id":"2101.08675","title":"Adversarial Machine Learning in Text Analysis and Generation","created":"2021-01-14","cited_by_count":2,"area":null},{"id":"2211.13003","title":"Detecting Conspiracy Theory Against COVID-19 Vaccines","created":"2022-11-20","cited_by_count":2,"area":null},{"id":"2406.17793","title":"Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networks","created":"2024-05-30","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":"2410.05573","title":"TaeBench: Improving Quality of Toxic Adversarial Examples","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2509.22699","title":"Are you sure? Measuring models bias in content moderation through uncertainty","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2112.06276","title":"Quantifying and Understanding Adversarial Examples in Discrete Input Spaces","created":"2021-12-12","cited_by_count":1,"area":null},{"id":"2307.06483","title":"Misclassification in Automated Content Analysis Causes Bias in Regression. Can We Fix It? Yes We Can!","created":"2023-07-12","cited_by_count":1,"area":null},{"id":"2402.19076","title":"Pointing out the Shortcomings of Relation Extraction Models with Semantically Motivated Adversarials","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2502.10921","title":"Evolving Hate Speech Online: An Adaptive Framework for Detection and Mitigation","created":"2025-02-15","cited_by_count":1,"area":null},{"id":"2505.16263","title":"All You Need is \"Leet\": Evading Hate-speech Detection AI","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2510.17924","title":"Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2601.20731","title":"QueerGen: How LLMs Reflect Societal Norms on Gender and Sexuality in Sentence Completion Tasks","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.06623","title":"Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2103.06130","title":"Stay on Topic, Please: Aligning User Comments to the Content of a News Article","created":"2021-03-03","cited_by_count":0,"area":null},{"id":"2109.01558","title":"Learning Neural Models for Natural Language Processing in the Face of Distributional Shift","created":"2021-09-03","cited_by_count":0,"area":null},{"id":"2201.02504","title":"Repairing Adversarial Texts through Perturbation","created":"2021-12-29","cited_by_count":0,"area":null},{"id":"2206.04162","title":"Improved two-stage hate speech classification for twitter based on Deep Neural Networks","created":"2022-06-08","cited_by_count":0,"area":null},{"id":"2207.10576","title":"Democratizing Ethical Assessment of Natural Language Generation Models","created":"2022-06-30","cited_by_count":0,"area":null},{"id":"2212.03279","title":"From Knowledge Augmentation to Multi-tasking: Towards Human-like Dialogue Systems","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2302.07872","title":"Data-Centric Governance","created":"2023-02-14","cited_by_count":0,"area":null},{"id":"2304.06934","title":"Classification of social media Toxic comments using Machine learning models","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2404.13065","title":"Intellecta Cognitiva: A Comprehensive Dataset for Advancing Academic Knowledge and Machine Reasoning","created":"2024-04-13","cited_by_count":0,"area":"lr"},{"id":"2409.09261","title":"What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicing","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2509.14622","title":"Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection","created":"2025-09-18","cited_by_count":0,"area":"rag"},{"id":"2509.17669","title":"PG-CE: A Progressive Generation Dataset with Constraint Enhancement for Controllable Text Generation","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2511.18790","title":"RoguePrompt: Dual-Layer Ciphering for Self-Reconstruction to Circumvent LLM Moderation","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2602.09343","title":"Not-in-Perspective: Towards Shielding Google's Perspective API Against Adversarial Negation Attacks","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2606.26936","title":"Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries","created":"2026-06-25","cited_by_count":0,"area":"safety"},{"id":"2607.27373","title":"RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation","created":"2026-07-29","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}