{"total":180,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"area":null},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040,"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":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"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":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"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":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","cited_by_count":195,"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":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"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":"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":"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":"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":"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":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63,"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":"2311.14125","title":"Scalable AI Safety via Doubly-Efficient Debate","created":"2023-11-23","cited_by_count":57,"area":null},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"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":"2504.10374","title":"Ctrl-Z: Controlling AI Agents via Resampling","created":"2025-04-14","cited_by_count":44,"area":null},{"id":"2311.08702","title":"Debate Helps Supervise Unreliable Experts","created":"2023-11-15","cited_by_count":43,"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":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2108.12099","title":"Learning to Give Checkable Answers with Prover-Verifier Games","created":"2021-08-27","cited_by_count":32,"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":"2401.11839","title":"AI for social science and social science of AI: A Survey","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2402.01704","title":"Steering Language Models with Game-Theoretic Solvers","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2412.18544","title":"Consistency Checks for Language Model Forecasters","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2311.11202","title":"Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models","created":"2023-11-19","cited_by_count":26,"area":null},{"id":"2204.05212","title":"Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions","created":"2022-04-11","cited_by_count":23,"area":null},{"id":"2310.02932","title":"Assessing Large Language Models on Climate Information","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2404.04289","title":"Designing for Human-Agent Alignment: Understanding what humans want from their agents","created":"2024-04-04","cited_by_count":18,"area":null},{"id":"2210.10860","title":"Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions","created":"2022-10-19","cited_by_count":17,"area":null},{"id":"2409.17213","title":"Plurals: A System for Guiding LLMs Via Simulated Social Ensembles","created":"2024-09-25","cited_by_count":17,"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":"2412.17128","title":"Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2506.13609","title":"Avoiding Obfuscation with Prover-Estimator Debate","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"area":null},{"id":"2109.00484","title":"Impossibility Results in AI: A Survey","created":"2021-09-01","cited_by_count":13,"area":null},{"id":"2503.22353","title":"Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions","created":"2025-03-28","cited_by_count":13,"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":"2411.02478","title":"Imagining and building wise machines: The centrality of AI metacognition","created":"2024-11-04","cited_by_count":12,"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":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10,"area":null},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2410.17781","title":"Evaluating Explanations Through LLMs: Beyond Traditional User Studies","created":"2024-10-23","cited_by_count":8,"area":null},{"id":"2501.13124","title":"Debate Helps Weak-to-Strong Generalization","created":"2025-01-21","cited_by_count":8,"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":"2506.17434","title":"Resource Rational Contractualism Should Guide AI Alignment","created":"2025-06-20","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2310.02457","title":"The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising \"Alignment\" in Large Language Models","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2405.15722","title":"Models That Prove Their Own Correctness","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2412.08897","title":"Neural Interactive Proofs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2312.04792","title":"Playing Large Games with Oracles and AI Debate","created":"2023-12-08","cited_by_count":6,"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":"2606.00424","title":"Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight","created":"2026-05-29","cited_by_count":6,"area":null},{"id":"2311.14708","title":"Large Language Model-Driven Classroom Flipping: Empowering Student-Centric Peer Questioning with Flipped Interaction","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2411.07965","title":"SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs","created":"2024-11-12","cited_by_count":5,"area":null},{"id":"2510.12826","title":"Scheming Ability in LLM-to-LLM Strategic Interactions","created":"2025-10-11","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":"2606.16475","title":"AI systems out-persuade expert humans","created":"2026-06-15","cited_by_count":5,"area":null},{"id":"2310.00378","title":"ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2401.16454","title":"KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants","created":"2024-01-29","cited_by_count":4,"area":null},{"id":"2510.13912","title":"AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2510.21332","title":"Weak-to-Strong Generalization under Distribution Shifts","created":"2025-10-24","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":"2105.06268","title":"Intelligence and Unambitiousness Using Algorithmic Information Theory","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2307.10987","title":"Characterising Decision Theories with Mechanised Causal Graphs","created":"2023-07-20","cited_by_count":3,"area":null},{"id":"2502.12995","title":"Free Argumentative Exchanges for Explaining Image Classifiers","created":"2025-02-18","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":"2504.06549","title":"Societal Impacts Research Requires Benchmarks for Creative Composition Tasks","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2506.06020","title":"When to Trust Context: Self-Reflective Debates for Context Reliability","created":"2025-06-06","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":"2510.26518","title":"Human-AI Complementarity: A Goal for Amplified Oversight","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2604.03588","title":"Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2102.03044","title":"Smart Proofs via Smart Contracts: Succinct and Informative Mathematical Derivations via Decentralized Markets","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2112.03799","title":"A pragmatic account of the weak evidence effect","created":"2021-12-07","cited_by_count":2,"area":null},{"id":"2408.08894","title":"Enhancing Exploratory Learning through Exploratory Search with the Emergence of Large Language Models","created":"2024-08-09","cited_by_count":2,"area":null},{"id":"2410.13215","title":"Balancing Label Quantity and Quality for Scalable Elicitation","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2410.17271","title":"Rules, Cases, and Reasoning: Positivist Legal Theory as a Framework for Pluralistic AI Alignment","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2505.02313","title":"What Is AI Safety? What Do We Want It to Be?","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2505.14886","title":"Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters","created":"2025-05-20","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":"2509.06858","title":"Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models","created":"2025-09-08","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}],"next_cursor":"100"}