{"list":"other","total":190,"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"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":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"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":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"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":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"1807.00459","title":"How To Backdoor Federated Learning","created":"2018-07-02","cited_by_count":765},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"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":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"1609.02943","title":"Stealing Machine Learning Models via Prediction APIs","created":"2016-09-09","cited_by_count":619},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"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":"2002.08347","title":"On Adaptive Attacks to Adversarial Example Defenses","created":"2020-02-19","cited_by_count":555},{"id":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"1804.00792","title":"Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks","created":"2018-04-03","cited_by_count":519},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2311.17035","title":"Scalable Extraction of Training Data from (Production) Language Models","created":"2023-11-28","cited_by_count":434},{"id":"2303.13408","title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","created":"2023-03-23","cited_by_count":429},{"id":"2007.08745","title":"Backdoor Learning: A Survey","created":"2020-07-17","cited_by_count":426},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387},{"id":"2303.11156","title":"Can AI-Generated Text be Reliably Detected?","created":"2023-03-17","cited_by_count":386},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2307.15593","title":"Robust Distortion-free Watermarks for Language Models","created":"2023-07-28","cited_by_count":320},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"1812.02766","title":"Knockoff Nets: Stealing Functionality of Black-Box Models","created":"2018-12-06","cited_by_count":292},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2007.08432","title":"Data Poisoning Attacks Against Federated Learning Systems","created":"2020-07-16","cited_by_count":275},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"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":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231},{"id":"2306.09194","title":"Undetectable Watermarks for Language Models","created":"2023-05-25","cited_by_count":226},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2006.07709","title":"Auditing Differentially Private Machine Learning: How Private is Private SGD?","created":"2020-06-13","cited_by_count":218},{"id":"1909.01838","title":"High Accuracy and High Fidelity Extraction of Neural Networks","created":"2019-09-03","cited_by_count":214},{"id":"2205.12628","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","created":"2022-05-25","cited_by_count":200},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200},{"id":"1708.08689","title":"Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization","created":"2017-08-29","cited_by_count":197},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195}],"next_cursor":"100"}