{"total":292,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512,"area":null},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819,"area":null},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767,"area":null},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651,"area":"alignment"},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"id":"2210.07242","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","created":"2022-10-13","cited_by_count":268,"area":null},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215,"area":null},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198,"area":null},{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2306.09301","title":"OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection","created":"2023-06-15","cited_by_count":179,"area":null},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"area":null},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155,"area":"alignment"},{"id":"2110.14051","title":"A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges","created":"2021-10-26","cited_by_count":154,"area":null},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"area":"safety"},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136,"area":"alignment"},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131,"area":null},{"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":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110,"area":null},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108,"area":null},{"id":"2402.18563","title":"Approaching Human-Level Forecasting with Language Models","created":"2024-02-28","cited_by_count":107,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"area":null},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2210.01478","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","created":"2022-10-04","cited_by_count":93,"area":null},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2405.14881","title":"DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models","created":"2024-04-05","cited_by_count":78,"area":"diffusion"},{"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":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63,"area":null},{"id":"2211.06291","title":"Do Bayesian Neural Networks Need To Be Fully Stochastic?","created":"2022-11-11","cited_by_count":63,"area":null},{"id":"2305.02231","title":"Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation","created":"2023-05-02","cited_by_count":61,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2206.05862","title":"X-Risk Analysis for AI Research","created":"2022-06-13","cited_by_count":60,"area":null},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2305.19713","title":"Red Teaming Language Model Detectors with Language Models","created":"2023-05-31","cited_by_count":55,"area":"safety"},{"id":"2310.17918","title":"Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method","created":"2023-10-27","cited_by_count":51,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2402.04247","title":"Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"area":"alignment"},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2402.18048","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","created":"2024-02-28","cited_by_count":45,"area":null},{"id":"2312.17199","title":"Tractable Function-Space Variational Inference in Bayesian Neural Networks","created":"2023-12-28","cited_by_count":41,"area":null},{"id":"2505.13763","title":"Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations","created":"2025-05-19","cited_by_count":41,"area":null},{"id":"2206.04199","title":"Deep Surrogate Assisted Generation of Environments","created":"2022-06-09","cited_by_count":40,"area":null},{"id":"2305.10613","title":"Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning","created":"2023-05-17","cited_by_count":37,"area":null},{"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":"2407.21794","title":"Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey","created":"2024-07-31","cited_by_count":36,"area":"mllm"},{"id":"2406.14477","title":"SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","created":"2024-06-20","cited_by_count":35,"area":"alignment"},{"id":"2303.08721","title":"Artificial Influence: An Analysis Of AI-Driven Persuasion","created":"2023-03-15","cited_by_count":33,"area":null},{"id":"2402.16006","title":"ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings","created":"2024-02-25","cited_by_count":32,"area":"safety"},{"id":"2311.09227","title":"Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives","created":"2023-09-29","cited_by_count":31,"area":null},{"id":"2206.11922","title":"Worldwide AI Ethics: a review of 200 guidelines and recommendations for AI governance","created":"2022-06-23","cited_by_count":28,"area":null},{"id":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2207.08645","title":"Active Exploration for Inverse Reinforcement Learning","created":"2022-07-18","cited_by_count":27,"area":"offlinerl"},{"id":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2305.19911","title":"Neuron to Graph: Interpreting Language Model Neurons at Scale","created":"2023-05-31","cited_by_count":27,"area":null},{"id":"2110.03922","title":"The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks","created":"2021-10-08","cited_by_count":26,"area":null},{"id":"2205.10752","title":"Covariance Matrix Adaptation MAP-Annealing","created":"2022-05-22","cited_by_count":25,"area":null},{"id":"2407.06443","title":"Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment","created":"2024-07-08","cited_by_count":25,"area":"alignment"},{"id":"2207.08089","title":"Threat Model-Agnostic Adversarial Defense using Diffusion Models","created":"2022-07-17","cited_by_count":24,"area":"diffusion"},{"id":"2303.16200","title":"Natural Selection Favors AIs over Humans","created":"2023-03-28","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2302.12461","title":"Analyzing And Editing Inner Mechanisms Of Backdoored Language Models","created":"2023-02-24","cited_by_count":23,"area":"safety"},{"id":"2204.06274","title":"Overparameterized Linear Regression under Adversarial Attacks","created":"2022-04-13","cited_by_count":21,"area":null},{"id":"2206.14157","title":"How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection","created":"2022-06-28","cited_by_count":21,"area":null},{"id":"2303.11341","title":"What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring","created":"2023-03-20","cited_by_count":21,"area":null},{"id":"2303.13500","title":"A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias","created":"2023-03-23","cited_by_count":20,"area":"mechinterp"},{"id":"2305.00851","title":"Revisiting Robustness in Graph Machine Learning","created":"2023-05-01","cited_by_count":19,"area":null},{"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":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18,"area":"alignment"},{"id":"2112.00659","title":"Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines","created":"2021-12-01","cited_by_count":17,"area":null},{"id":"2403.15879","title":"TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring","created":"2024-03-23","cited_by_count":17,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2505.12709","title":"Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics","created":"2025-05-19","cited_by_count":17,"area":null},{"id":"2601.02671","title":"Extracting books from production language models","created":"2026-01-06","cited_by_count":17,"area":"safety"},{"id":"2503.13868","title":"Out-of-Distribution Generalization in Time Series: A Survey","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2207.11378","title":"Do Perceptually Aligned Gradients Imply Adversarial Robustness?","created":"2022-07-22","cited_by_count":15,"area":null},{"id":"2311.01550","title":"Market Concentration Implications of Foundation Models","created":"2023-11-02","cited_by_count":15,"area":null},{"id":"2312.15297","title":"Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models","created":"2023-12-23","cited_by_count":15,"area":null}],"next_cursor":"100"}