{"list":"other","total":214,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"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":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","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":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"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":"1609.02943","title":"Stealing Machine Learning Models via Prediction APIs","created":"2016-09-09","cited_by_count":619},{"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":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2305.13860","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","created":"2023-05-23","cited_by_count":498},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"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":"2007.08745","title":"Backdoor Learning: A Survey","created":"2020-07-17","cited_by_count":426},{"id":"2212.03860","title":"Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models","created":"2022-12-07","cited_by_count":424},{"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":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398},{"id":"2007.14321","title":"Label-Only Membership Inference Attacks","created":"2020-07-28","cited_by_count":388},{"id":"2309.07875","title":"Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions","created":"2023-09-14","cited_by_count":387},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"2310.10501","title":"NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails","created":"2023-10-16","cited_by_count":365},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2011.10369","title":"ONION: A Simple and Effective Defense Against Textual Backdoor Attacks","created":"2020-11-20","cited_by_count":263},{"id":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232},{"id":"1905.12457","title":"A backdoor attack against LSTM-based text classification systems","created":"2019-05-29","cited_by_count":227},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222},{"id":"2311.08401","title":"Fine-tuning Language Models for Factuality","created":"2023-11-14","cited_by_count":221},{"id":"2202.07785","title":"Predictability and Surprise in Large Generative Models","created":"2022-02-15","cited_by_count":210},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205},{"id":"2004.00053","title":"Information Leakage in Embedding Models","created":"2020-03-31","cited_by_count":203},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192},{"id":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191},{"id":"2301.01768","title":"The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation","created":"2023-01-05","cited_by_count":189},{"id":"2305.12082","title":"SneakyPrompt: Jailbreaking Text-to-image Generative Models","created":"2023-05-20","cited_by_count":189},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","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":"2311.05553","title":"Removing RLHF Protections in GPT-4 via Fine-Tuning","created":"2023-11-09","cited_by_count":171},{"id":"1506.02753","title":"Inverting Visual Representations with Convolutional Networks","created":"2015-06-09","cited_by_count":170},{"id":"2311.09096","title":"Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization","created":"2023-11-15","cited_by_count":170},{"id":"2102.02503","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","created":"2021-02-04","cited_by_count":160},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158},{"id":"2301.04246","title":"Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations","created":"2023-01-10","cited_by_count":158},{"id":"2307.16888","title":"Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection","created":"2023-07-31","cited_by_count":157}],"next_cursor":"100"}