{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"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},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2002.08347","title":"On Adaptive Attacks to Adversarial Example Defenses","created":"2020-02-19","cited_by_count":555},{"id":"2305.13860","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","created":"2023-05-23","cited_by_count":498},{"id":"2311.17035","title":"Scalable Extraction of Training Data from (Production) Language Models","created":"2023-11-28","cited_by_count":434},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2307.15593","title":"Robust Distortion-free Watermarks for Language Models","created":"2023-07-28","cited_by_count":320},{"id":"2306.17439","title":"Provable Robust Watermarking for AI-Generated Text","created":"2023-06-30","cited_by_count":299},{"id":"1907.06515","title":"Detecting and Simulating Artifacts in GAN Fake Images","created":"2019-07-15","cited_by_count":293},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244},{"id":"2306.09194","title":"Undetectable Watermarks for Language Models","created":"2023-05-25","cited_by_count":226},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161},{"id":"2311.01011","title":"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game","created":"2023-11-02","cited_by_count":145},{"id":"2307.00691","title":"From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy","created":"2023-07-03","cited_by_count":143},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135},{"id":"2311.14455","title":"Universal Jailbreak Backdoors from Poisoned Human Feedback","created":"2023-11-24","cited_by_count":128},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96},{"id":"2209.02128","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","created":"2022-09-05","cited_by_count":69},{"id":"2204.04741","title":"Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?","created":"2022-04-10","cited_by_count":67},{"id":"2307.14192","title":"Unveiling Security, Privacy, and Ethical Concerns of ChatGPT","created":"2023-07-26","cited_by_count":53},{"id":"2309.10254","title":"LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Plugins","created":"2023-09-19","cited_by_count":51},{"id":"2307.10719","title":"LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?","created":"2023-07-20","cited_by_count":49},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48},{"id":"2312.07930","title":"Towards Optimal Statistical Watermarking","created":"2023-12-13","cited_by_count":26},{"id":"2312.02798","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","created":"2023-12-05","cited_by_count":20}],"next_cursor":null}