{"list":"other","total":87,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"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":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"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":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"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":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375},{"id":"2310.12815","title":"Formalizing and Benchmarking Prompt Injection Attacks and Defenses","created":"2023-10-19","cited_by_count":364},{"id":"1801.04354","title":"Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers","created":"2018-01-13","cited_by_count":345},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316},{"id":"1804.06059","title":"Adversarial Example Generation with Syntactically Controlled Paraphrase Networks","created":"2018-04-17","cited_by_count":286},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278},{"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":"2304.07590","title":"Self-collaboration Code Generation via ChatGPT","created":"2023-04-15","cited_by_count":258},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2311.17516","title":"MMA-Diffusion: MultiModal Attack on Diffusion Models","created":"2023-11-29","cited_by_count":194},{"id":"2305.12082","title":"SneakyPrompt: Jailbreaking Text-to-image Generative Models","created":"2023-05-20","cited_by_count":189},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"1710.11342","title":"Generating Natural Adversarial Examples","created":"2017-10-31","cited_by_count":183},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177},{"id":"2402.16893","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","created":"2024-02-23","cited_by_count":159},{"id":"2405.15556","title":"Certifiably Robust RAG against Retrieval Corruption","created":"2024-05-24","cited_by_count":151},{"id":"2311.01011","title":"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game","created":"2023-11-02","cited_by_count":145},{"id":"2312.04724","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","created":"2023-12-07","cited_by_count":138},{"id":"2401.03428","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","created":"2024-01-07","cited_by_count":132},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130},{"id":"2405.06823","title":"PLeak: Prompt Leaking Attacks against Large Language Model Applications","created":"2024-05-10","cited_by_count":127},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127},{"id":"2310.13345","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","created":"2023-10-20","cited_by_count":116},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"1903.11508","title":"Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems","created":"2019-03-27","cited_by_count":101},{"id":"2306.00924","title":"Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker","created":"2023-06-01","cited_by_count":95},{"id":"2310.02374","title":"Conversational Health Agents: A Personalized LLM-Powered Agent Framework","created":"2023-10-03","cited_by_count":92},{"id":"2402.14020","title":"Coercing LLMs to do and reveal (almost) anything","created":"2024-02-21","cited_by_count":89},{"id":"2402.19464","title":"Curiosity-driven Red-teaming for Large Language Models","created":"2024-02-29","cited_by_count":88},{"id":"2403.17336","title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","created":"2024-03-26","cited_by_count":86},{"id":"2307.06865","title":"Effective Prompt Extraction from Language Models","created":"2023-07-13","cited_by_count":85},{"id":"2009.09191","title":"OpenAttack: An Open-source Textual Adversarial Attack Toolkit","created":"2020-09-19","cited_by_count":84},{"id":"2308.04265","title":"FLIRT: Feedback Loop In-context Red Teaming","created":"2023-08-08","cited_by_count":83},{"id":"1809.03627","title":"ClusterGAN : Latent Space Clustering in Generative Adversarial Networks","created":"2018-09-10","cited_by_count":75},{"id":"2404.08031","title":"Latent Guard: a Safety Framework for Text-to-image Generation","created":"2024-04-11","cited_by_count":71},{"id":"2407.15186","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","created":"2024-07-21","cited_by_count":67},{"id":"2403.02817","title":"Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications","created":"2024-03-05","cited_by_count":59},{"id":"2308.01990","title":"From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?","created":"2023-08-03","cited_by_count":55},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54},{"id":"2309.05274","title":"FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models","created":"2023-09-11","cited_by_count":51},{"id":"2305.01526","title":"Huatuo-26M, a Large-scale Chinese Medical QA Dataset","created":"2023-05-02","cited_by_count":46},{"id":"2311.09948","title":"Hijacking Large Language Models via Adversarial In-Context Learning","created":"2023-11-16","cited_by_count":45},{"id":"2308.04451","title":"Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks","created":"2023-08-04","cited_by_count":33},{"id":"2105.11136","title":"Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models","created":"2021-05-24","cited_by_count":29},{"id":"2403.09751","title":"What Was Your Prompt? A Remote Keylogging Attack on AI Assistants","created":"2024-03-14","cited_by_count":26},{"id":"2405.13966","title":"On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models","created":"2024-05-22","cited_by_count":17},{"id":"2403.09060","title":"GenRewrite: Query Rewriting via Large Language Models","created":"2024-03-14","cited_by_count":12},{"id":"2402.03628","title":"Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies","created":"2024-02-06","cited_by_count":9},{"id":"2408.02416","title":"Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models","created":"2024-08-05","cited_by_count":9},{"id":"2312.07553","title":"Hijacking Context in Large Multi-modal Models","created":"2023-12-07","cited_by_count":6},{"id":"2306.04874","title":"Expanding Scope: Adapting English Adversarial Attacks to Chinese","created":"2023-06-08","cited_by_count":3},{"id":"2403.15325","title":"A Technological Perspective on Misuse of Available AI","created":"2024-03-22","cited_by_count":3}],"next_cursor":null}