{"list":"other","total":52,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"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":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489},{"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":"2305.16367","title":"Role-Play with Large Language Models","created":"2023-05-25","cited_by_count":294},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2012.15761","title":"Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection","created":"2020-12-31","cited_by_count":221},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2307.08715","title":"MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots","created":"2023-07-16","cited_by_count":183},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173},{"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":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151},{"id":"2402.14016","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","created":"2024-02-21","cited_by_count":126},{"id":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98},{"id":"2312.12575","title":"LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks","created":"2023-12-19","cited_by_count":97},{"id":"2405.05610","title":"Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM","created":"2024-05-09","cited_by_count":77},{"id":"2402.16192","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","created":"2024-02-25","cited_by_count":74},{"id":"2408.13296","title":"The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities","created":"2024-08-23","cited_by_count":64},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55},{"id":"2403.04786","title":"Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models","created":"2024-03-03","cited_by_count":44},{"id":"2402.12959","title":"Prompt Stealing Attacks Against Large Language Models","created":"2024-02-20","cited_by_count":40},{"id":"2309.11852","title":"Knowledge Sanitization of Large Language Models","created":"2023-09-21","cited_by_count":37},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37},{"id":"2401.12273","title":"The Ethics of Interaction: Mitigating Security Threats in LLMs","created":"2024-01-22","cited_by_count":33},{"id":"2405.14487","title":"A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions","created":"2024-05-23","cited_by_count":33},{"id":"2006.02633","title":"Stopwords in Technical Language Processing","created":"2020-06-04","cited_by_count":29},{"id":"2404.10779","title":"Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations","created":"2024-03-23","cited_by_count":28},{"id":"2408.04585","title":"Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness","created":"2024-08-08","cited_by_count":22},{"id":"2410.12851","title":"VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models","created":"2024-10-10","cited_by_count":17},{"id":"2407.00747","title":"A Comparative Study of Quality Evaluation Methods for Text Summarization","created":"2024-06-30","cited_by_count":13},{"id":"2308.14608","title":"AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics","created":"2023-08-28","cited_by_count":12},{"id":"2409.11026","title":"Prompt Obfuscation for Large Language Models","created":"2024-09-17","cited_by_count":10},{"id":"2310.11593","title":"Automated Evaluation of Personalized Text Generation using Large Language Models","created":"2023-10-17","cited_by_count":9},{"id":"2405.03654","title":"Can LLMs Deeply Detect Complex Malicious Queries? A Framework for Jailbreaking via Obfuscating Intent","created":"2024-05-06","cited_by_count":8},{"id":"2408.07004","title":"Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models","created":"2024-08-13","cited_by_count":8},{"id":"2407.20529","title":"Can LLMs be Fooled? Investigating Vulnerabilities in LLMs","created":"2024-07-30","cited_by_count":5},{"id":"2410.17222","title":"Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods","created":"2024-10-22","cited_by_count":4},{"id":"2403.14469","title":"ChatGPT Alternative Solutions: Large Language Models Survey","created":"2024-03-21","cited_by_count":2},{"id":"2105.00824","title":"A Survey of Recent Abstract Summarization Techniques","created":"2021-04-15","cited_by_count":1}],"next_cursor":null}