{"list":"other","total":220,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2312.11805","title":"Gemini: A Family of Highly Capable Multimodal Models","created":"2023-12-19","cited_by_count":872},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2401.06373","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","created":"2024-01-12","cited_by_count":573},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2305.13860","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","created":"2023-05-23","cited_by_count":498},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"2311.17035","title":"Scalable Extraction of Training Data from (Production) Language Models","created":"2023-11-28","cited_by_count":434},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"2310.02238","title":"Who's Harry Potter? Approximate Unlearning in LLMs","created":"2023-10-03","cited_by_count":381},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309},{"id":"2310.10683","title":"Large Language Model Unlearning","created":"2023-10-14","cited_by_count":302},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2312.14197","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","created":"2023-12-21","cited_by_count":264},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"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":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215},{"id":"2310.20150","title":"Unlearn What You Want to Forget: Efficient Unlearning for LLMs","created":"2023-10-31","cited_by_count":215},{"id":"2311.03348","title":"Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation","created":"2023-11-06","cited_by_count":214},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2310.07298","title":"Beyond Memorization: Violating Privacy Via Inference with Large Language Models","created":"2023-10-11","cited_by_count":175},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172},{"id":"2010.07079","title":"Recipes for Safety in Open-domain Chatbots","created":"2020-10-14","cited_by_count":170},{"id":"1802.07228","title":"The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation","created":"2018-02-20","cited_by_count":165},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156},{"id":"2205.10487","title":"Scaling Laws and Interpretability of Learning from Repeated Data","created":"2022-05-21","cited_by_count":152},{"id":"2007.07646","title":"A Survey of Privacy Attacks in Machine Learning","created":"2020-07-15","cited_by_count":146},{"id":"2311.07590","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","created":"2023-11-09","cited_by_count":146},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143},{"id":"2305.15060","title":"Who Wrote this Code? Watermarking for Code Generation","created":"2023-05-24","cited_by_count":141},{"id":"2312.04724","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","created":"2023-12-07","cited_by_count":138},{"id":"2304.05332","title":"Emergent autonomous scientific research capabilities of large language models","created":"2023-04-11","cited_by_count":132},{"id":"2403.13793","title":"Evaluating Frontier Models for Dangerous Capabilities","created":"2024-03-20","cited_by_count":128},{"id":"2010.02428","title":"UnQovering Stereotyping Biases via Underspecified Questions","created":"2020-10-06","cited_by_count":126},{"id":"2404.12253","title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","created":"2024-04-18","cited_by_count":125},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115},{"id":"2310.15140","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","created":"2023-10-23","cited_by_count":111},{"id":"2405.21018","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","created":"2024-05-31","cited_by_count":110},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107},{"id":"2311.11855","title":"Evil Geniuses: Delving into the Safety of LLM-based Agents","created":"2023-11-20","cited_by_count":106},{"id":"2206.07271","title":"Human heuristics for AI-generated language are flawed","created":"2022-06-15","cited_by_count":105},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101}],"next_cursor":"100"}