{"total":513,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297,"area":"rag"},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744,"area":null},{"id":"2301.11305","title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature","created":"2023-01-26","cited_by_count":726,"area":null},{"id":"2301.07597","title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection","created":"2023-01-18","cited_by_count":481,"area":null},{"id":"2303.11156","title":"Can AI-Generated Text be Reliably Detected?","created":"2023-03-17","cited_by_count":386,"area":"safety"},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366,"area":null},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356,"area":"diffusion"},{"id":"2310.05130","title":"Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature","created":"2023-10-08","cited_by_count":287,"area":null},{"id":"2401.12070","title":"Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text","created":"2024-01-22","cited_by_count":263,"area":null},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2402.11753","title":"ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs","created":"2024-02-19","cited_by_count":216,"area":"safety"},{"id":"2306.05540","title":"DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text","created":"2023-05-23","cited_by_count":210,"area":null},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198,"area":null},{"id":"2210.17432","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","created":"2022-10-31","cited_by_count":194,"area":"diffusion"},{"id":"2307.03838","title":"RADAR: Robust AI-Text Detection via Adversarial Learning","created":"2023-07-07","cited_by_count":190,"area":null},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189,"area":"safety"},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187,"area":null},{"id":"2304.02819","title":"GPT detectors are biased against non-native English writers","created":"2023-04-06","cited_by_count":178,"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":"2403.07183","title":"Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews","created":"2024-03-11","cited_by_count":164,"area":null},{"id":"2405.07940","title":"RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors","created":"2024-05-13","cited_by_count":163,"area":null},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150,"area":null},{"id":"2304.03738","title":"Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models","created":"2023-04-07","cited_by_count":148,"area":null},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141,"area":null},{"id":"2305.15060","title":"Who Wrote this Code? Watermarking for Code Generation","created":"2023-05-24","cited_by_count":141,"area":"safety"},{"id":"2305.17359","title":"DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text","created":"2023-05-27","cited_by_count":129,"area":null},{"id":"2108.02818","title":"Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications","created":"2021-08-05","cited_by_count":128,"area":null},{"id":"2303.07205","title":"The Science of Detecting LLM-Generated Texts","created":"2023-02-04","cited_by_count":128,"area":null},{"id":"2305.14902","title":"M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection","created":"2023-05-24","cited_by_count":121,"area":null},{"id":"2109.13296","title":"TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation","created":"2021-09-27","cited_by_count":120,"area":null},{"id":"2404.01268","title":"Mapping the Increasing Use of LLMs in Scientific Papers","created":"2024-04-01","cited_by_count":118,"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":"2306.04723","title":"Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts","created":"2023-06-07","cited_by_count":112,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"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":"2303.14822","title":"MGTBench: Benchmarking Machine-Generated Text Detection","created":"2023-03-26","cited_by_count":93,"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":"2305.15047","title":"Ghostbuster: Detecting Text Ghostwritten by Large Language Models","created":"2023-05-24","cited_by_count":91,"area":null},{"id":"2306.17806","title":"Stay on topic with Classifier-Free Guidance","created":"2023-06-30","cited_by_count":91,"area":null},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"area":null},{"id":"2206.09511","title":"The Fallacy of AI Functionality","created":"2022-06-20","cited_by_count":88,"area":null},{"id":"2304.04736","title":"On the Possibilities of AI-Generated Text Detection","created":"2023-04-10","cited_by_count":88,"area":null},{"id":"2107.08720","title":"Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech","created":"2021-07-19","cited_by_count":82,"area":null},{"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":"2312.04469","title":"On the Learnability of Watermarks for Language Models","created":"2023-12-07","cited_by_count":81,"area":"safety"},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80,"area":null},{"id":"2307.11729","title":"OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples","created":"2023-07-21","cited_by_count":80,"area":null},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"area":null},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2402.00045","title":"Detecting Multimedia Generated by Large AI Models: A Survey","created":"2024-01-22","cited_by_count":76,"area":"diffusion"},{"id":"2310.15654","title":"A Survey on Detection of LLMs-Generated Content","created":"2023-10-24","cited_by_count":71,"area":null},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2403.07918","title":"On the Societal Impact of Open Foundation Models","created":"2024-02-27","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":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2101.09157","title":"The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2305.18149","title":"Multiscale Positive-Unlabeled Detection of AI-Generated Texts","created":"2023-05-29","cited_by_count":61,"area":null},{"id":"2303.03697","title":"Stylometric Detection of AI-Generated Text in Twitter Timelines","created":"2023-03-07","cited_by_count":59,"area":null},{"id":"2211.14946","title":"Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models","created":"2022-11-27","cited_by_count":57,"area":null},{"id":"2310.08903","title":"SeqXGPT: Sentence-Level AI-Generated Text Detection","created":"2023-10-13","cited_by_count":56,"area":null},{"id":"2305.19713","title":"Red Teaming Language Model Detectors with Language Models","created":"2023-05-31","cited_by_count":55,"area":"safety"},{"id":"2307.15992","title":"Towards Codable Watermarking for Injecting Multi-bits Information to LLMs","created":"2023-07-29","cited_by_count":54,"area":"safety"},{"id":"2404.08080","title":"Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models","created":"2024-04-11","cited_by_count":54,"area":null},{"id":"2306.13731","title":"How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images","created":"2023-06-23","cited_by_count":53,"area":null},{"id":"2401.12970","title":"Raidar: geneRative AI Detection viA Rewriting","created":"2024-01-23","cited_by_count":52,"area":null},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","cited_by_count":51,"area":null},{"id":"2307.13808","title":"Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy","created":"2023-07-25","cited_by_count":50,"area":"safety"},{"id":"2402.16187","title":"No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices","created":"2024-02-25","cited_by_count":50,"area":"safety"},{"id":"2409.15875","title":"Zero-Shot Detection of AI-Generated Images","created":"2024-09-24","cited_by_count":50,"area":null},{"id":"2410.07698","title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","created":"2024-10-10","cited_by_count":50,"area":null},{"id":"2411.04125","title":"Community Forensics: Using Thousands of Generators to Train Fake Image Detectors","created":"2024-11-06","cited_by_count":50,"area":null},{"id":"2109.04825","title":"Artificial Text Detection via Examining the Topology of Attention Maps","created":"2021-09-10","cited_by_count":49,"area":null},{"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":"2310.16523","title":"Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting","created":"2023-10-25","cited_by_count":46,"area":null},{"id":"2302.07267","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","created":"2023-02-13","cited_by_count":45,"area":"lr"},{"id":"2305.15004","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","created":"2023-05-24","cited_by_count":45,"area":null},{"id":"2305.10847","title":"Large Language Models can be Guided to Evade AI-Generated Text Detection","created":"2023-05-18","cited_by_count":44,"area":null},{"id":"2305.07969","title":"GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content","created":"2023-05-13","cited_by_count":43,"area":null},{"id":"2402.11175","title":"M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection","created":"2024-02-17","cited_by_count":43,"area":null},{"id":"2106.11783","title":"Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech","created":"2021-06-22","cited_by_count":42,"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":"2410.04265","title":"AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text","created":"2024-10-05","cited_by_count":42,"area":null},{"id":"2201.05159","title":"Structured access: an emerging paradigm for safe AI deployment","created":"2022-01-13","cited_by_count":41,"area":null},{"id":"2304.12008","title":"CHEAT: A Large-scale Dataset for Detecting ChatGPT-writtEn AbsTracts","created":"2023-04-24","cited_by_count":40,"area":null},{"id":"2304.14072","title":"Origin Tracing and Detecting of LLMs","created":"2023-04-27","cited_by_count":40,"area":null},{"id":"2310.06202","title":"GPT-who: An Information Density-based Machine-Generated Text Detector","created":"2023-10-09","cited_by_count":40,"area":null},{"id":"2401.06712","title":"Few-Shot Detection of Machine-Generated Text using Style Representations","created":"2024-01-12","cited_by_count":40,"area":null},{"id":"2501.15654","title":"People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text","created":"2025-01-26","cited_by_count":40,"area":null},{"id":"2308.01284","title":"Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?","created":"2023-08-02","cited_by_count":39,"area":null},{"id":"2305.09820","title":"Machine-Made Media: Monitoring the Mobilization of Machine-Generated Articles on Misinformation and Mainstream News Websites","created":"2023-05-16","cited_by_count":38,"area":null},{"id":"2410.23746","title":"DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios","created":"2024-10-31","cited_by_count":38,"area":null},{"id":"2210.09421","title":"Deepfake Text Detection: Limitations and Opportunities","created":"2022-10-17","cited_by_count":37,"area":null},{"id":"2402.12948","title":"GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick","created":"2024-02-20","cited_by_count":37,"area":"safety"}],"next_cursor":"100"}