{"total":263,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398,"area":"mllm"},{"id":"2402.01145","title":"ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution","created":"2024-02-02","cited_by_count":276,"area":null},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264,"area":"alignment"},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229,"area":"safety"},{"id":"2402.07456","title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","created":"2024-02-12","cited_by_count":205,"area":"agents"},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128,"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":"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":"2405.20974","title":"SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales","created":"2024-05-31","cited_by_count":105,"area":null},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2507.01925","title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","created":"2025-07-02","cited_by_count":96,"area":"vla"},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2402.16192","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","created":"2024-02-25","cited_by_count":74,"area":"alignment"},{"id":"2503.03480","title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","created":"2025-03-05","cited_by_count":72,"area":"vla"},{"id":"2402.04559","title":"Can Large Language Model Agents Simulate Human Trust Behavior?","created":"2024-02-07","cited_by_count":64,"area":"agents"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2402.17385","title":"Determinants of LLM-assisted Decision-Making","created":"2024-02-27","cited_by_count":56,"area":null},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54,"area":"alignment"},{"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":"2501.13381","title":"Do as We Do, Not as You Think: the Conformity of Large Language Models","created":"2025-01-23","cited_by_count":53,"area":"lr"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2402.10946","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","created":"2024-02-09","cited_by_count":50,"area":null},{"id":"2510.25445","title":"Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions","created":"2025-10-29","cited_by_count":48,"area":"agents"},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2410.04350","title":"TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights","created":"2024-10-06","cited_by_count":42,"area":"alignment"},{"id":"2404.09824","title":"Impact of Preference Noise on the Alignment Performance of Generative Language Models","created":"2024-04-15","cited_by_count":41,"area":"alignment"},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41,"area":null},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2409.00598","title":"Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models","created":"2024-09-01","cited_by_count":35,"area":"alignment"},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34,"area":"safety"},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2503.08663","title":"Generating Robot Constitutions & Benchmarks for Semantic Safety","created":"2025-03-11","cited_by_count":33,"area":null},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2406.09321","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","created":"2024-06-13","cited_by_count":31,"area":"safety"},{"id":"2404.11049","title":"Stepwise Alignment for Constrained Language Model Policy Optimization","created":"2024-04-17","cited_by_count":30,"area":"alignment"},{"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":"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":"2402.15505","title":"Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts","created":"2024-02-23","cited_by_count":28,"area":"moe"},{"id":"2401.17268","title":"Weaver: Foundation Models for Creative Writing","created":"2024-01-30","cited_by_count":27,"area":null},{"id":"2406.18676","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","created":"2024-06-26","cited_by_count":27,"area":"rag"},{"id":"2408.04655","title":"Strong and weak alignment of large language models with human values","created":"2024-08-05","cited_by_count":27,"area":"alignment"},{"id":"2409.19605","title":"The Crucial Role of Samplers in Online Direct Preference Optimization","created":"2024-09-29","cited_by_count":27,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2505.15456","title":"Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment","created":"2025-05-21","cited_by_count":24,"area":null},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"id":"2501.07238","title":"Lessons From Red Teaming 100 Generative AI Products","created":"2025-01-13","cited_by_count":23,"area":"safety"},{"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":"2508.01674","title":"CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions","created":"2025-08-03","cited_by_count":22,"area":null},{"id":"2407.12344","title":"The Better Angels of Machine Personality: How Personality Relates to LLM Safety","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2410.09713","title":"Agentic Information Retrieval","created":"2024-10-13","cited_by_count":21,"area":"agents"},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21,"area":"alignment"},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2401.15071","title":"From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities","created":"2024-01-26","cited_by_count":19,"area":"mllm"},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2404.05264","title":"Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security","created":"2024-04-08","cited_by_count":19,"area":"mllm"},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2410.18141","title":"SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback","created":"2024-10-22","cited_by_count":19,"area":"rag"},{"id":"2411.17636","title":"MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation","created":"2024-11-26","cited_by_count":19,"area":"agents"},{"id":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2405.17345","title":"Exploring and steering the moral compass of Large Language Models","created":"2024-05-27","cited_by_count":16,"area":null},{"id":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2503.18130","title":"Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization","created":"2025-03-23","cited_by_count":14,"area":"alignment"},{"id":"2405.15185","title":"An Evaluation of Estimative Uncertainty in Large Language Models","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2409.12106","title":"Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2412.04139","title":"Monet: Mixture of Monosemantic Experts for Transformers","created":"2024-12-05","cited_by_count":13,"area":"mechinterp"},{"id":"2503.14504","title":"Aligning Multimodal LLM with Human Preference: A Survey","created":"2025-03-18","cited_by_count":13,"area":"mllm"},{"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":"2505.18154","title":"The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2505.18531","title":"Generative RLHF-V: Learning Principles from Multi-modal Human Preference","created":"2025-05-24","cited_by_count":13,"area":"mllm"},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2601.04583","title":"Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries","created":"2026-01-08","cited_by_count":13,"area":"agents"},{"id":"2411.02478","title":"Imagining and building wise machines: The centrality of AI metacognition","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2412.10380","title":"Challenges in Human-Agent Communication","created":"2024-11-28","cited_by_count":12,"area":"agents"},{"id":"2507.07341","title":"On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment","created":"2025-07-09","cited_by_count":12,"area":"safety"},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2311.06330","title":"Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations","created":"2023-11-10","cited_by_count":11,"area":"agents"},{"id":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","cited_by_count":11,"area":null},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2412.15623","title":"JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs","created":"2024-12-20","cited_by_count":11,"area":"alignment"},{"id":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2504.00285","title":"When Do Large Language Models Exhibit Unsolicited Deception?","created":"2025-03-31","cited_by_count":10,"area":null},{"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":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"},{"id":"2510.06871","title":"SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2402.02346","title":"Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback","created":"2024-02-04","cited_by_count":9,"area":"diffusion"}],"next_cursor":"100"}