{"list":"other","total":85,"rows":[{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536},{"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":"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":"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":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"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":"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":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244},{"id":"2407.21772","title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","created":"2024-07-31","cited_by_count":243},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2404.03027","title":"JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks","created":"2024-04-03","cited_by_count":230},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185},{"id":"2307.08715","title":"MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots","created":"2023-07-16","cited_by_count":183},{"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":"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":"2311.09096","title":"Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization","created":"2023-11-15","cited_by_count":170},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156},{"id":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136},{"id":"2501.09004","title":"Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails","created":"2025-01-15","cited_by_count":132},{"id":"2504.13203","title":"X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents","created":"2025-04-15","cited_by_count":125},{"id":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113},{"id":"2405.21018","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","created":"2024-05-31","cited_by_count":110},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98},{"id":"2402.13494","title":"GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis","created":"2024-02-21","cited_by_count":96},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95},{"id":"2405.18166","title":"Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing","created":"2024-05-28","cited_by_count":79},{"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":"2412.03556","title":"Best-of-N Jailbreaking","created":"2024-12-04","cited_by_count":76},{"id":"2403.00867","title":"Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes","created":"2024-03-01","cited_by_count":74},{"id":"2310.01432","title":"Split and Merge: Aligning Position Biases in LLM-based Evaluators","created":"2023-09-29","cited_by_count":72},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69},{"id":"2402.09091","title":"Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues","created":"2024-02-14","cited_by_count":68},{"id":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67},{"id":"2402.17262","title":"Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue","created":"2024-02-27","cited_by_count":66},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63},{"id":"2502.07557","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","created":"2025-02-11","cited_by_count":54},{"id":"2404.05880","title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge","created":"2024-04-08","cited_by_count":51},{"id":"2402.09674","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","created":"2024-02-15","cited_by_count":50},{"id":"2406.08705","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search","created":"2024-06-13","cited_by_count":47},{"id":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43},{"id":"2401.16765","title":"A Cross-Language Investigation into Jailbreak Attacks in Large Language Models","created":"2024-01-30","cited_by_count":41},{"id":"2409.03788","title":"HSF: Defending against Jailbreak Attacks with Hidden State Filtering","created":"2024-08-31","cited_by_count":23},{"id":"2405.04160","title":"A Causal Explainable Guardrails for Large Language Models","created":"2024-05-07","cited_by_count":18},{"id":"2411.07494","title":"Rapid Response: Mitigating LLM Jailbreaks with a Few Examples","created":"2024-11-12","cited_by_count":16},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14},{"id":"2403.00826","title":"LLMGuard: Guarding Against Unsafe LLM Behavior","created":"2024-02-27","cited_by_count":13},{"id":"2504.08848","title":"X-Guard: Multilingual Guard Agent for Content Moderation","created":"2025-04-11","cited_by_count":13},{"id":"2408.08343","title":"API-guided Dataset Synthesis to Finetune Large Code Models","created":"2024-08-15","cited_by_count":11},{"id":"2501.18638","title":"Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation","created":"2025-01-28","cited_by_count":11},{"id":"2407.16318","title":"PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing","created":"2024-07-23","cited_by_count":10},{"id":"2412.01547","title":"Improved Large Language Model Jailbreak Detection via Pretrained Embeddings","created":"2024-12-02","cited_by_count":10},{"id":"2502.19041","title":"Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs","created":"2025-02-26","cited_by_count":9},{"id":"2408.08959","title":"Trust-Oriented Adaptive Guardrails for Large Language Models","created":"2024-08-16","cited_by_count":8},{"id":"2412.18171","title":"Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models","created":"2024-12-24","cited_by_count":7},{"id":"2406.03230","title":"Defending Large Language Models Against Attacks With Residual Stream Activation Analysis","created":"2024-06-05","cited_by_count":5},{"id":"2504.19440","title":"JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift","created":"2025-04-28","cited_by_count":5},{"id":"2409.17699","title":"MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks","created":"2024-09-26","cited_by_count":3},{"id":"2503.17932","title":"STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models","created":"2025-03-23","cited_by_count":3},{"id":"2503.12931","title":"MirrorShield: Towards Universal Defense Against Jailbreaks via Entropy-Guided Mirror Crafting","created":"2025-03-17","cited_by_count":1}],"next_cursor":null}