{"total":529,"rows":[{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536,"area":"safety"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2410.02644","title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","created":"2024-10-03","cited_by_count":369,"area":"agents"},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360,"area":"alignment"},{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"area":null},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266,"area":"alignment"},{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265,"area":null},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223,"area":"safety"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2605.29358","title":"Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet","created":"2026-05-28","cited_by_count":191,"area":"mechinterp"},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178,"area":null},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2402.11208","title":"Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents","created":"2024-02-17","cited_by_count":137,"area":"agents"},{"id":"2511.18397","title":"Natural Emergent Misalignment from Reward Hacking in Production RL","created":"2025-11-23","cited_by_count":136,"area":"alignment"},{"id":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131,"area":"agents"},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2503.00061","title":"Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents","created":"2025-02-27","cited_by_count":125,"area":"agents"},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"area":"alignment"},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113,"area":"agents"},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2507.14805","title":"Subliminal Learning: Language models transmit behavioral traits via hidden signals in data","created":"2025-07-20","cited_by_count":95,"area":null},{"id":"2506.11613","title":"Model Organisms for Emergent Misalignment","created":"2025-06-13","cited_by_count":91,"area":null},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2407.12831","title":"Truth is Universal: Robust Detection of Lies in LLMs","created":"2024-07-03","cited_by_count":79,"area":null},{"id":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77,"area":"alignment"},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72,"area":"alignment"},{"id":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72,"area":"safety"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2506.11618","title":"Convergent Linear Representations of Emergent Misalignment","created":"2025-06-13","cited_by_count":71,"area":null},{"id":"2401.12255","title":"Instructional Fingerprinting of Large Language Models","created":"2024-01-21","cited_by_count":68,"area":null},{"id":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68,"area":"safety"},{"id":"2405.13401","title":"TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models","created":"2024-05-22","cited_by_count":67,"area":"rag"},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"id":"2411.09523","title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","created":"2024-11-14","cited_by_count":65,"area":"agents"},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2509.26354","title":"Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents","created":"2025-09-30","cited_by_count":62,"area":"agents"},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58,"area":"safety"},{"id":"2403.02910","title":"ImgTrojan: Jailbreaking Vision-Language Models with ONE Image","created":"2024-03-05","cited_by_count":57,"area":"mllm"},{"id":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56,"area":"lr"},{"id":"2402.00786","title":"CroissantLLM: A Truly Bilingual French-English Language Model","created":"2024-02-01","cited_by_count":53,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"area":null},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50,"area":"safety"},{"id":"2405.20485","title":"Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation","created":"2024-05-30","cited_by_count":49,"area":"rag"},{"id":"2410.13722","title":"Persistent Pre-Training Poisoning of LLMs","created":"2024-10-17","cited_by_count":48,"area":null},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47,"area":"alignment"},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2406.19501","title":"Monitoring Latent World States in Language Models with Propositional Probes","created":"2024-06-27","cited_by_count":43,"area":"wm"},{"id":"2405.01576","title":"Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2407.10887","title":"Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2406.06852","title":"A Survey of Recent Backdoor Attacks and Defenses in Large Language Models","created":"2024-06-10","cited_by_count":36,"area":"safety"},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35,"area":null},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2509.23886","title":"Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer","created":"2025-09-28","cited_by_count":34,"area":"distill"},{"id":"2403.04801","title":"Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs","created":"2024-03-05","cited_by_count":33,"area":"agents"},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"id":"2411.12768","title":"CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization","created":"2024-11-18","cited_by_count":33,"area":"safety"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2409.09013","title":"AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents","created":"2024-09-13","cited_by_count":31,"area":"agents"},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2404.01231","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2505.18889","title":"Security Concerns for Large Language Models: A Survey","created":"2025-05-24","cited_by_count":29,"area":null},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2604.09378","title":"BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning","created":"2026-04-10","cited_by_count":27,"area":"safety"},{"id":"2605.15338","title":"Hidden in Memory: Sleeper Memory Poisoning in LLM Agents","created":"2026-05-14","cited_by_count":27,"area":"agents"},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25,"area":"safety"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2403.00108","title":"LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem","created":"2024-02-29","cited_by_count":24,"area":null},{"id":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24,"area":"safety"},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","cited_by_count":24,"area":"safety"},{"id":"2602.07852","title":"Emergent Misalignment is Easy, Narrow Misalignment is Hard","created":"2026-02-08","cited_by_count":23,"area":null},{"id":"2402.10196","title":"A Trembling House of Cards? Mapping Adversarial Attacks against Language Agents","created":"2024-02-15","cited_by_count":22,"area":"agents"},{"id":"2510.19851","title":"Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability","created":"2025-10-21","cited_by_count":22,"area":"lr"},{"id":"2511.20703","title":"PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach","created":"2025-11-24","cited_by_count":22,"area":"agents"},{"id":"2512.08093","title":"Training LLMs for Honesty via Confessions","created":"2025-12-08","cited_by_count":22,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2507.14293","title":"WebGuard: Building a Generalizable Guardrail for Web Agents","created":"2025-07-18","cited_by_count":21,"area":"agents"},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2409.19998","title":"Do Influence Functions Work on Large Language Models?","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2601.11369","title":"Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs","created":"2026-01-16","cited_by_count":20,"area":"agents"},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2506.16447","title":"Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18,"area":null}],"next_cursor":"100"}