{"total":199,"rows":[{"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,"area":"safety"},{"id":"2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","created":"2025-05-29","cited_by_count":356,"area":"agents"},{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244,"area":"alignment"},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130,"area":null},{"id":"2411.10414","title":"Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations","created":"2024-11-15","cited_by_count":129,"area":"mllm"},{"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":"2404.16698","title":"Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents","created":"2024-04-25","cited_by_count":125,"area":"wm"},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"area":"safety"},{"id":"2410.08948","title":"Emergent social conventions and collective bias in LLM populations","created":"2024-10-11","cited_by_count":123,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2502.14881","title":"A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations","created":"2025-02-14","cited_by_count":67,"area":"mllm"},{"id":"2405.18137","title":"Exploiting LLM Quantization","created":"2024-05-28","cited_by_count":65,"area":null},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"area":null},{"id":"2406.09400","title":"Yo'LLaVA: Your Personalized Language and Vision Assistant","created":"2024-06-13","cited_by_count":62,"area":"mllm"},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55,"area":"safety"},{"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,"area":"safety"},{"id":"2406.07057","title":"MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models","created":"2024-06-11","cited_by_count":53,"area":"mllm"},{"id":"2407.06576","title":"Virtual Personas for Language Models via an Anthology of Backstories","created":"2024-07-09","cited_by_count":51,"area":null},{"id":"2405.00592","title":"Scaling and renormalization in high-dimensional regression","created":"2024-05-01","cited_by_count":50,"area":null},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"area":"mechinterp"},{"id":"2410.13722","title":"Persistent Pre-Training Poisoning of LLMs","created":"2024-10-17","cited_by_count":48,"area":null},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44,"area":"lr"},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40,"area":"safety"},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"area":"lr"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2405.10467","title":"Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents","created":"2024-05-16","cited_by_count":35,"area":"agents"},{"id":"2410.12735","title":"CREAM: Consistency Regularized Self-Rewarding Language Models","created":"2024-10-16","cited_by_count":35,"area":"lr"},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2503.17682","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback","created":"2025-03-22","cited_by_count":30,"area":"mllm"},{"id":"2411.03343","title":"What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks","created":"2024-11-02","cited_by_count":29,"area":"safety"},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29,"area":null},{"id":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2511.00617","title":"Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering","created":"2025-11-01","cited_by_count":29,"area":"mechinterp"},{"id":"2404.14461","title":"Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs","created":"2024-04-22","cited_by_count":28,"area":"safety"},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2502.11355","title":"Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents","created":"2025-02-17","cited_by_count":27,"area":"lr"},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"id":"2408.12578","title":"A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language","created":"2024-08-22","cited_by_count":26,"area":null},{"id":"2501.16173","title":"Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma","created":"2025-01-27","cited_by_count":25,"area":"agents"},{"id":"2505.17863","title":"The emergence of sparse attention: impact of data distribution and benefits of repetition","created":"2025-05-23","cited_by_count":25,"area":null},{"id":"2404.18353","title":"How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2405.19544","title":"One-Shot Safety Alignment for Large Language Models via Optimal Dualization","created":"2024-05-29","cited_by_count":24,"area":"alignment"},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2503.10566","title":"ASIDE: Architectural Separation of Instructions and Data in Language Models","created":"2025-03-13","cited_by_count":24,"area":"safety"},{"id":"2502.11090","title":"SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks","created":"2025-02-16","cited_by_count":23,"area":"safety"},{"id":"2407.02209","title":"Generative Monoculture in Large Language Models","created":"2024-07-02","cited_by_count":22,"area":null},{"id":"2407.20224","title":"Can Editing LLMs Inject Harm?","created":"2024-07-29","cited_by_count":22,"area":"safety"},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2506.04018","title":"AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents","created":"2025-06-04","cited_by_count":22,"area":"agents"},{"id":"2406.07954","title":"Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition","created":"2024-06-12","cited_by_count":20,"area":null},{"id":"2501.14940","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","created":"2025-01-24","cited_by_count":20,"area":"alignment"},{"id":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2411.08790","title":"Can sparse autoencoders be used to decompose and interpret steering vectors?","created":"2024-11-13","cited_by_count":19,"area":"mechinterp"},{"id":"2502.16320","title":"Direct Alignment with Heterogeneous Preferences","created":"2025-02-22","cited_by_count":19,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2406.10630","title":"Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models","created":"2024-06-15","cited_by_count":18,"area":"alignment"},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2407.15645","title":"Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2508.05687","title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","created":"2025-08-06","cited_by_count":18,"area":"agents"},{"id":"2410.02684","title":"HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router","created":"2024-10-03","cited_by_count":16,"area":"safety"},{"id":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2510.22422","title":"Group size effects and collective misalignment in LLM multi-agent systems","created":"2025-10-25","cited_by_count":16,"area":"agents"},{"id":"2412.07942","title":"Neural Scaling Laws Rooted in the Data Distribution","created":"2024-12-10","cited_by_count":15,"area":null},{"id":"2502.01635","title":"The AI Agent Index","created":"2025-02-03","cited_by_count":15,"area":"agents"},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2405.10799","title":"Training Compute Thresholds: Features and Functions in AI Regulation","created":"2024-05-17","cited_by_count":14,"area":null},{"id":"2410.18819","title":"From Imitation to Introspection: Probing Self-Consciousness in Language Models","created":"2024-10-24","cited_by_count":14,"area":null},{"id":"2506.06298","title":"Pairwise Calibrated Rewards for Pluralistic Alignment","created":"2025-05-17","cited_by_count":14,"area":"alignment"},{"id":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","cited_by_count":13,"area":"agents"},{"id":"2505.17646","title":"Unveiling the Basin-Like Loss Landscape in Large Language Models","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2501.11739","title":"Episodic memory in AI agents poses risks that should be studied and mitigated","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2504.15047","title":"RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search","created":"2025-04-21","cited_by_count":11,"area":"safety"},{"id":"2506.06278","title":"Distillation Robustifies Unlearning","created":"2025-06-06","cited_by_count":11,"area":"safety"},{"id":"2512.05648","title":"Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs","created":"2025-12-05","cited_by_count":11,"area":"safety"},{"id":"2411.16035","title":"Predicting Emergent Capabilities by Finetuning","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2504.20965","title":"AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security","created":"2025-04-29","cited_by_count":10,"area":"agents"},{"id":"2505.03439","title":"The Steganographic Potentials of Language Models","created":"2025-05-06","cited_by_count":10,"area":"lr"},{"id":"2505.19241","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2508.09853","title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2404.18870","title":"More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness","created":"2024-04-29","cited_by_count":9,"area":"alignment"},{"id":"2406.20087","title":"ProgressGym: Alignment with a Millennium of Moral Progress","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2501.09254","title":"Clone-Robust AI Alignment","created":"2025-01-16","cited_by_count":9,"area":"alignment"},{"id":"2502.15427","title":"Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs","created":"2025-02-21","cited_by_count":9,"area":"safety"}],"next_cursor":"100"}