{"list":"other","total":55,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"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":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437},{"id":"2404.01833","title":"Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack","created":"2024-04-02","cited_by_count":390},{"id":"2402.10260","title":"A StrongREJECT for Empty Jailbreaks","created":"2024-02-15","cited_by_count":385},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","created":"2025-01-31","cited_by_count":181},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173},{"id":"1805.02628","title":"PRADA: Protecting against DNN Model Stealing Attacks","created":"2018-05-07","cited_by_count":165},{"id":"2408.08926","title":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models","created":"2024-08-15","cited_by_count":164},{"id":"2407.10362","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","created":"2024-07-14","cited_by_count":156},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"id":"2403.13793","title":"Evaluating Frontier Models for Dangerous Capabilities","created":"2024-03-20","cited_by_count":128},{"id":"2411.01111","title":"Rule Based Rewards for Language Model Safety","created":"2024-11-02","cited_by_count":108},{"id":"2402.16914","title":"DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers","created":"2024-02-25","cited_by_count":101},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96},{"id":"2406.20053","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","created":"2024-06-28","cited_by_count":80},{"id":"2412.13678","title":"Clio: Privacy-Preserving Insights into Real-World AI Use","created":"2024-12-18","cited_by_count":72},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61},{"id":"1907.05587","title":"Stateful Detection of Black-Box Adversarial Attacks","created":"2019-07-12","cited_by_count":56},{"id":"2502.03461","title":"Do Large Language Model Benchmarks Test Reliability?","created":"2025-02-05","cited_by_count":54},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52},{"id":"2412.09565","title":"Obfuscated Activations Bypass LLM Latent-Space Defenses","created":"2024-12-12","cited_by_count":45},{"id":"2006.14042","title":"Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks","created":"2020-06-24","cited_by_count":37},{"id":"2312.15838","title":"SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security","created":"2023-12-26","cited_by_count":37},{"id":"2505.01420","title":"Evaluating Frontier Models for Stealth and Situational Awareness","created":"2025-05-02","cited_by_count":37},{"id":"2311.00117","title":"BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B","created":"2023-10-31","cited_by_count":36},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32},{"id":"2504.16137","title":"Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark","created":"2025-04-21","cited_by_count":31},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29},{"id":"2504.10694","title":"The Jailbreak Tax: How Useful are Your Jailbreak Outputs?","created":"2025-04-14","cited_by_count":28},{"id":"2407.02551","title":"Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses","created":"2024-07-02","cited_by_count":18},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15},{"id":"2303.06280","title":"Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks","created":"2023-03-11","cited_by_count":11}],"next_cursor":null}