{"total":159,"rows":[{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832,"area":null},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732,"area":null},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"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":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225,"area":null},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"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":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149,"area":null},{"id":"2306.15063","title":"Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression","created":"2023-06-26","cited_by_count":146,"area":null},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105,"area":null},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"area":null},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100,"area":null},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99,"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":"2307.00175","title":"Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks","created":"2023-06-30","cited_by_count":78,"area":null},{"id":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2312.01037","title":"Eliciting Latent Knowledge from Quirky Language Models","created":"2023-12-02","cited_by_count":62,"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":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"area":null},{"id":"2506.05233","title":"MesaNet: Sequence Modeling by Locally Optimal Test-Time Training","created":"2025-06-05","cited_by_count":47,"area":null},{"id":"2507.16003","title":"Learning without training: The implicit dynamics of in-context learning","created":"2025-07-21","cited_by_count":43,"area":null},{"id":"2202.05780","title":"A Modern Self-Referential Weight Matrix That Learns to Modify Itself","created":"2022-02-11","cited_by_count":41,"area":null},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"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":"2505.01420","title":"Evaluating Frontier Models for Stealth and Situational Awareness","created":"2025-05-02","cited_by_count":37,"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":"2406.00877","title":"Evidence of Learned Look-Ahead in a Chess-Playing Neural Network","created":"2024-06-02","cited_by_count":34,"area":null},{"id":"2411.03336","title":"Towards evaluations-based safety cases for AI scheming","created":"2024-10-29","cited_by_count":33,"area":null},{"id":"2502.12206","title":"Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?","created":"2025-02-16","cited_by_count":33,"area":null},{"id":"2411.02544","title":"Pretrained transformer efficiently learns low-dimensional target functions in-context","created":"2024-11-04","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":"2208.12852","title":"What Do NLP Researchers Believe? Results of the NLP Community Metasurvey","created":"2022-08-26","cited_by_count":28,"area":null},{"id":"2402.14180","title":"Linear Transformers are Versatile In-Context Learners","created":"2024-02-21","cited_by_count":28,"area":null},{"id":"2303.16200","title":"Natural Selection Favors AIs over Humans","created":"2023-03-28","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":"2311.07772","title":"In-context Learning and Gradient Descent Revisited","created":"2023-11-13","cited_by_count":20,"area":null},{"id":"2206.13477","title":"Parametrically Retargetable Decision-Makers Tend To Seek Power","created":"2022-06-27","cited_by_count":19,"area":null},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2410.13211","title":"Estimating the Probabilities of Rare Outputs in Language Models","created":"2024-10-17","cited_by_count":16,"area":null},{"id":"2505.03989","title":"An alignment safety case sketch based on debate","created":"2025-05-06","cited_by_count":16,"area":null},{"id":"2307.10569","title":"Deceptive Alignment Monitoring","created":"2023-07-20","cited_by_count":14,"area":null},{"id":"2402.02212","title":"A Survey to Recent Progress Towards Understanding In-Context Learning","created":"2024-02-03","cited_by_count":14,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2302.00805","title":"Conditioning Predictive Models: Risks and Strategies","created":"2023-02-02","cited_by_count":11,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2305.17601","title":"Incentivizing honest performative predictions with proper scoring rules","created":"2023-05-28","cited_by_count":9,"area":null},{"id":"2507.17951","title":"Are LLM Belief Updates Consistent with Bayes' Theorem?","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2502.16840","title":"In-context Learning of Evolving Data Streams with Tabular Foundational Models","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2206.02841","title":"Researching Alignment Research: Unsupervised Analysis","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2206.08966","title":"Actionable Guidance for High-Consequence AI Risk Management: Towards Standards Addressing AI Catastrophic Risks","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2410.04683","title":"Towards Measuring Goal-Directedness in AI Systems","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2504.20084","title":"AI Awareness","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2604.21098","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2211.10024","title":"Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2508.14927","title":"AI Testing Should Account for Sophisticated Strategic Behaviour","created":"2025-08-19","cited_by_count":6,"area":null},{"id":"2310.14455","title":"An International Consortium for Evaluations of Societal-Scale Risks from Advanced AI","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2405.16845","title":"On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2603.10028","title":"How to Count AIs: Individuation and Liability for AI Agents","created":"2026-02-24","cited_by_count":5,"area":null},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2506.21584","title":"Empirical Evidence for Alignment Faking in a Small LLM and Prompt-Based Mitigation Techniques","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2510.10425","title":"Softmax $\\geq$ Linear: Transformers may learn to classify in-context by kernel gradient descent","created":"2025-10-12","cited_by_count":4,"area":null},{"id":"2604.22082","title":"Removing Sandbagging in LLMs by Training with Weak Supervision","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2605.26438","title":"LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2110.06890","title":"Extending Environments To Measure Self-Reflection In Reinforcement Learning","created":"2021-10-13","cited_by_count":3,"area":null},{"id":"2410.10596","title":"Overcoming classic challenges for artificial neural networks by providing incentives and practice","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2506.02923","title":"The Limits of Predicting Agents from Behaviour","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2506.17846","title":"Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)","created":"2025-06-21","cited_by_count":3,"area":null},{"id":"2507.02977","title":"LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2509.04445","title":"Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment","created":"2025-09-04","cited_by_count":3,"area":null},{"id":"2509.08592","title":"Interpretability as Alignment: Making Internal Understanding a Design Principle","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2604.20995","title":"Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2605.05176","title":"Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2210.09366","title":"Bridging the Gap between Artificial Intelligence and Artificial General Intelligence: A Ten Commandment Framework for Human-Like Intelligence","created":"2022-10-17","cited_by_count":2,"area":null},{"id":"2407.00805","title":"Towards Shutdownable Agents via Stochastic Choice","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2409.03077","title":"Backdoor defense, learnability and obfuscation","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2503.04750","title":"AI Agents Should be Regulated Based on the Extent of Their Autonomous Operations","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2505.22829","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.03056","title":"Corrigibility as a Singular Target: A Vision for Inherently Reliable Foundation Models","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2507.22255","title":"Agent-centric learning: from external reward maximization to internal knowledge curation","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2508.19562","title":"Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2602.05656","title":"Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.24126","title":"Likelihood Hacking in Probabilistic Program Synthesis","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null}],"next_cursor":"100"}