{"total":66,"rows":[{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"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":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380,"area":null},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"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":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"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":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"area":null},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105,"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":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2312.01037","title":"Eliciting Latent Knowledge from Quirky Language Models","created":"2023-12-02","cited_by_count":62,"area":null},{"id":"2311.14125","title":"Scalable AI Safety via Doubly-Efficient Debate","created":"2023-11-23","cited_by_count":57,"area":null},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"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":"2402.04477","title":"Detecting Mode Collapse in Language Models via Narration","created":"2024-02-06","cited_by_count":24,"area":null},{"id":"2310.02932","title":"Assessing Large Language Models on Climate Information","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2311.08576","title":"Towards Evaluating AI Systems for Moral Status Using Self-Reports","created":"2023-11-14","cited_by_count":22,"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":"2302.13137","title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","created":"2023-02-25","cited_by_count":15,"area":null},{"id":"2406.04604","title":"Learning Task Decomposition to Assist Humans in Competitive Programming","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2506.13609","title":"Avoiding Obfuscation with Prover-Estimator Debate","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2411.16905","title":"Boundless Socratic Learning with Language Games","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2501.13124","title":"Debate Helps Weak-to-Strong Generalization","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2104.08647","title":"Question Decomposition with Dependency Graphs","created":"2021-04-17","cited_by_count":7,"area":null},{"id":"2405.09794","title":"Human-AI Safety: A Descendant of Generative AI and Control Systems Safety","created":"2024-05-16","cited_by_count":7,"area":null},{"id":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7,"area":null},{"id":"2402.12907","title":"Roadmap on Incentive Compatibility for AI Alignment and Governance in Sociotechnical Systems","created":"2024-02-20","cited_by_count":6,"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":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2606.12683","title":"From AGI to ASI","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2311.04046","title":"Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features","created":"2023-11-07","cited_by_count":3,"area":null},{"id":"2410.01064","title":"Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2503.22989","title":"FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2504.03731","title":"A Benchmark for Scalable Oversight Protocols","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2510.26518","title":"Human-AI Complementarity: A Goal for Amplified Oversight","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2606.29604","title":"Mechanistically Eliciting Latent Behaviors in Language Models","created":"2026-06-28","cited_by_count":3,"area":null},{"id":"2504.17404","title":"Super Co-alignment of Human and AI for Sustainable Symbiotic Society","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2510.13551","title":"Tandem Training for Language Models","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2605.01643","title":"AI Alignment via Incentives and Correction","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.06390","title":"Automated alignment is harder than you think","created":"2026-05-07","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},{"id":"2510.11235","title":"AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2606.28639","title":"Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2608.26582","title":"J-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2507.11502","title":"HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.21131","title":"NPO: Learning Alignment and Meta-Alignment through Structured Human Feedback","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2510.22500","title":"Towards Scalable Oversight via Partitioned Human Supervision","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2604.08606","title":"Extrapolating Volition with Recursive Information Markets","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.14990","title":"The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.04070","title":"Toward Human-AI Complementarity Across Diverse Tasks","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.07724","title":"Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.30863","title":"Beyond expert users: agents should help users construct preferences, not just elicit them","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.07040","title":"Measuring Intelligence Beyond Human Scale","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.06422","title":"Sharding Prevents LLM Oversight Failures and Adversarial Exploitation","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.02095","title":"READY or Not: Reliable Enterprise Agent Deployment","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.24895","title":"Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.29189","title":"When Honesty is Not Enough in AI Debate","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36049","title":"Improving scalable oversight with co-trained monitors","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01995","title":"Can AI Oversight Be Zero Knowledge?","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.10064","title":"Comprehension Audits to Mitigate Risks from Automated AI Research","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}