{"total":158,"rows":[{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588,"area":null},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651,"area":"safety"},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443,"area":"safety"},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395,"area":"agents"},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785,"area":"alignment"},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259,"area":"safety"},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2303.10130","title":"GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models","created":"2023-03-17","cited_by_count":176,"area":null},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2305.13661","title":"On the Risk of Misinformation Pollution with Large Language Models","created":"2023-05-23","cited_by_count":128,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2302.02337","title":"Regulating ChatGPT and other Large Generative AI Models","created":"2023-02-05","cited_by_count":104,"area":null},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2306.04141","title":"Art and the science of generative AI: A deeper dive","created":"2023-06-07","cited_by_count":95,"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":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2305.01904","title":"Robust Multi-bit Natural Language Watermarking through Invariant Features","created":"2023-05-03","cited_by_count":82,"area":"safety"},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2312.00273","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","created":"2023-12-01","cited_by_count":71,"area":"safety"},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"id":"2501.09674","title":"Authenticated Delegation and Authorized AI Agents","created":"2025-01-16","cited_by_count":65,"area":null},{"id":"2302.04844","title":"The Gradient of Generative AI Release: Methods and Considerations","created":"2023-02-05","cited_by_count":63,"area":null},{"id":"2307.14192","title":"Unveiling Security, Privacy, and Ethical Concerns of ChatGPT","created":"2023-07-26","cited_by_count":53,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48,"area":"safety"},{"id":"2402.03299","title":"GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models","created":"2024-02-05","cited_by_count":48,"area":"safety"},{"id":"2304.09991","title":"Supporting Human-AI Collaboration in Auditing LLMs with LLMs","created":"2023-04-19","cited_by_count":46,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2503.03710","title":"Improving LLM Safety Alignment with Dual-Objective Optimization","created":"2025-03-05","cited_by_count":43,"area":"alignment"},{"id":"2402.10426","title":"DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection","created":"2024-02-16","cited_by_count":41,"area":null},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2311.05915","title":"Fake Alignment: Are LLMs Really Aligned Well?","created":"2023-11-10","cited_by_count":39,"area":null},{"id":"2412.06878","title":"SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations","created":"2024-12-09","cited_by_count":38,"area":"safety"},{"id":"2311.06899","title":"Flames: Benchmarking Value Alignment of LLMs in Chinese","created":"2023-11-12","cited_by_count":37,"area":"alignment"},{"id":"2307.16336","title":"Anatomy of an AI-powered malicious social botnet","created":"2023-07-30","cited_by_count":36,"area":null},{"id":"2310.10077","title":"Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks","created":"2023-10-16","cited_by_count":35,"area":"safety"},{"id":"2412.13879","title":"Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings","created":"2024-12-18","cited_by_count":35,"area":null},{"id":"2312.12807","title":"All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models","created":"2023-12-20","cited_by_count":33,"area":"diffusion"},{"id":"2311.09227","title":"Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives","created":"2023-09-29","cited_by_count":31,"area":null},{"id":"2501.05171","title":"Emergence of polarization in networks of large language model agents","created":"2025-01-09","cited_by_count":26,"area":"agents"},{"id":"2311.08838","title":"Disinformation Capabilities of Large Language Models","created":"2023-11-15","cited_by_count":25,"area":null},{"id":"2312.17295","title":"Optimizing watermarks for large language models","created":"2023-12-28","cited_by_count":25,"area":"safety"},{"id":"2312.04127","title":"Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak","created":"2023-12-07","cited_by_count":23,"area":"safety"},{"id":"2407.10725","title":"CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses","created":"2024-07-15","cited_by_count":23,"area":null},{"id":"2410.08044","title":"The Rise of AI-Generated Content in Wikipedia","created":"2024-10-10","cited_by_count":22,"area":null},{"id":"2401.07348","title":"Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity","created":"2024-01-14","cited_by_count":21,"area":null},{"id":"2404.00750","title":"Can Language Models Recognize Convincing Arguments?","created":"2024-03-31","cited_by_count":21,"area":null},{"id":"2407.14321","title":"Multimodal Misinformation Detection using Large Vision-Language Models","created":"2024-07-19","cited_by_count":21,"area":"mllm"},{"id":"2406.13843","title":"Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data","created":"2024-06-19","cited_by_count":20,"area":null},{"id":"2412.13666","title":"Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation","created":"2024-12-18","cited_by_count":20,"area":null},{"id":"2507.13919","title":"The Levers of Political Persuasion with Conversational AI","created":"2025-07-18","cited_by_count":20,"area":null},{"id":"2402.15265","title":"CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models","created":"2024-02-23","cited_by_count":19,"area":null},{"id":"2407.03453","title":"On Large Language Models in National Security Applications","created":"2024-07-03","cited_by_count":19,"area":null},{"id":"2305.12519","title":"DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection","created":"2023-05-21","cited_by_count":18,"area":null},{"id":"2405.13058","title":"The AI Community Building the Future? A Quantitative Analysis of Development Activity on Hugging Face Hub","created":"2024-05-20","cited_by_count":18,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2410.04068","title":"ECon: On the Detection and Resolution of Evidence Conflicts","created":"2024-10-05","cited_by_count":18,"area":null},{"id":"2303.06074","title":"Susceptibility to Influence of Large Language Models","created":"2023-03-10","cited_by_count":17,"area":null},{"id":"2308.03740","title":"A Cost Analysis of Generative Language Models and Influence Operations","created":"2023-08-07","cited_by_count":17,"area":null},{"id":"2303.09377","title":"Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?","created":"2023-03-16","cited_by_count":16,"area":null},{"id":"2311.01550","title":"Market Concentration Implications of Foundation Models","created":"2023-11-02","cited_by_count":15,"area":null},{"id":"2412.17128","title":"Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2311.04917","title":"Adapting Fake News Detection to the Era of Large Language Models","created":"2023-11-02","cited_by_count":14,"area":null},{"id":"2401.02627","title":"Characteristics and prevalence of fake social media profiles with AI-generated faces","created":"2024-01-05","cited_by_count":14,"area":null},{"id":"2504.09865","title":"Labeling Messages as AI-Generated Does Not Reduce Their Persuasive Effects","created":"2025-04-14","cited_by_count":13,"area":null},{"id":"2312.07141","title":"Multilingual large language models leak human stereotypes across language boundaries","created":"2023-12-12","cited_by_count":12,"area":null},{"id":"2409.09041","title":"Acceptable Use Policies for Foundation Models","created":"2024-08-29","cited_by_count":12,"area":null},{"id":"2411.14133","title":"GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs","created":"2024-11-21","cited_by_count":12,"area":"safety"},{"id":"2311.14711","title":"Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework","created":"2023-11-15","cited_by_count":11,"area":null},{"id":"2402.16578","title":"Multi-Bit Distortion-Free Watermarking for Large Language Models","created":"2024-02-26","cited_by_count":11,"area":"safety"},{"id":"2406.14508","title":"Evidence of a log scaling law for political persuasion with large language models","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2507.14660","title":"When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems","created":"2025-07-19","cited_by_count":11,"area":null},{"id":"2309.03164","title":"J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News","created":"2023-09-06","cited_by_count":10,"area":null},{"id":"2404.14244","title":"AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images","created":"2024-04-22","cited_by_count":10,"area":null},{"id":"2407.13089","title":"MetaSumPerceiver: Multimodal Multi-Document Evidence Summarization for Fact-Checking","created":"2024-07-18","cited_by_count":10,"area":null},{"id":"2403.12077","title":"Evaluating Robustness of Generative Search Engine on Adversarial Factual Questions","created":"2024-02-25","cited_by_count":9,"area":"rag"},{"id":"2406.20087","title":"ProgressGym: Alignment with a Millennium of Moral Progress","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2505.00036","title":"A Framework to Assess the Persuasion Risks Large Language Model Chatbots Pose to Democratic Societies","created":"2025-04-29","cited_by_count":9,"area":null},{"id":"2308.15514","title":"International Governance of Civilian AI: A Jurisdictional Certification Approach","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2405.00711","title":"Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities","created":"2024-04-25","cited_by_count":8,"area":"diffusion"},{"id":"2501.17273","title":"Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics","created":"2025-01-28","cited_by_count":8,"area":null},{"id":"2405.20657","title":"DORY: Deliberative Prompt Recovery for LLM","created":"2024-05-31","cited_by_count":7,"area":null},{"id":"2406.18725","title":"Jailbreaking LLMs with Arabic Transliteration and Arabizi","created":"2024-06-26","cited_by_count":7,"area":"safety"},{"id":"2409.08895","title":"Synthetic Human Memories: AI-Edited Images and Videos Can Implant False Memories and Distort Recollection","created":"2024-09-13","cited_by_count":7,"area":null},{"id":"2401.06829","title":"Cross-Attention Watermarking of Large Language Models","created":"2024-01-12","cited_by_count":6,"area":"safety"},{"id":"2508.19292","title":"Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience","created":"2025-08-25","cited_by_count":6,"area":"safety"},{"id":"2404.10496","title":"Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering","created":"2024-04-16","cited_by_count":5,"area":"rag"},{"id":"2409.06729","title":"How will advanced AI systems impact democracy?","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2410.12600","title":"On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMs","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2505.21608","title":"How does Misinformation Affect Large Language Model Behaviors and Preferences?","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2509.07287","title":"Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2407.04794","title":"On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks","created":"2024-07-05","cited_by_count":4,"area":"safety"},{"id":"2409.03291","title":"LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2412.00357","title":"Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models","created":"2024-11-30","cited_by_count":4,"area":"diffusion"},{"id":"2505.13531","title":"AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2506.07211","title":"Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2508.20186","title":"AI Propaganda factories with language models","created":"2025-08-27","cited_by_count":4,"area":null}],"next_cursor":"100"}