{"total":164,"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":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323,"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":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225,"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":"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":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"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":"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":"2406.14805","title":"How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions","created":"2024-06-21","cited_by_count":52,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2311.08702","title":"Debate Helps Supervise Unreliable Experts","created":"2023-11-15","cited_by_count":43,"area":null},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"area":null},{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40,"area":null},{"id":"2311.05915","title":"Fake Alignment: Are LLMs Really Aligned Well?","created":"2023-11-10","cited_by_count":39,"area":null},{"id":"2306.01386","title":"ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?","created":"2023-06-02","cited_by_count":38,"area":null},{"id":"2311.08993","title":"When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks","created":"2023-11-15","cited_by_count":37,"area":null},{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","cited_by_count":33,"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":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","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":"2204.12993","title":"Counterfactual harm","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2401.02994","title":"Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM","created":"2024-01-04","cited_by_count":27,"area":null},{"id":"2310.00533","title":"SELF: Self-Evolution with Language Feedback","created":"2023-10-01","cited_by_count":24,"area":null},{"id":"2507.03041","title":"Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards","created":"2025-07-03","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":"2310.02932","title":"Assessing Large Language Models on Climate Information","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2207.14157","title":"A Hazard Analysis Framework for Code Synthesis Large Language Models","created":"2022-07-25","cited_by_count":22,"area":null},{"id":"2310.08043","title":"Understanding and Controlling a Maze-Solving Policy Network","created":"2023-10-12","cited_by_count":22,"area":null},{"id":"2311.00710","title":"Interactive AI Alignment: Specification, Process, and Evaluation Alignment","created":"2023-10-23","cited_by_count":22,"area":null},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2305.16147","title":"Learning Safety Constraints from Demonstrations with Unknown Rewards","created":"2023-05-25","cited_by_count":19,"area":null},{"id":"2502.03369","title":"Learning from Active Human Involvement through Proxy Value Propagation","created":"2025-02-05","cited_by_count":19,"area":null},{"id":"2404.01954","title":"HyperCLOVA X Technical Report","created":"2024-04-02","cited_by_count":18,"area":null},{"id":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18,"area":null},{"id":"2307.01189","title":"Trainable Transformer in Transformer","created":"2023-07-03","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":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","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":"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":"2403.13592","title":"Llama meets EU: Investigating the European Political Spectrum through the Lens of LLMs","created":"2024-03-20","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":"2405.08597","title":"Risks and Opportunities of Open-Source Generative AI","created":"2024-05-14","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":"2303.13360","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","created":"2023-03-16","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":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2504.00285","title":"When Do Large Language Models Exhibit Unsolicited Deception?","created":"2025-03-31","cited_by_count":10,"area":null},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2406.04231","title":"Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment","created":"2024-06-06","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":"2505.18139","title":"Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems","created":"2025-05-23","cited_by_count":8,"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":"2405.02288","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2501.09766","title":"iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use","created":"2025-01-15","cited_by_count":7,"area":null},{"id":"2502.04695","title":"Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance","created":"2025-02-07","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":"2405.06424","title":"Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation","created":"2024-05-10","cited_by_count":6,"area":null},{"id":"2502.07237","title":"DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2512.05379","title":"Mitigating Self-Preference by Authorship Obfuscation","created":"2025-12-05","cited_by_count":6,"area":null},{"id":"2202.10600","title":"Myriad: a real-world testbed to bridge trajectory optimization and deep learning","created":"2022-02-22","cited_by_count":5,"area":null},{"id":"2310.05553","title":"Regulation and NLP (RegNLP): Taming Large Language Models","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2406.04584","title":"CLoG: Benchmarking Continual Learning of Image Generation Models","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2409.13697","title":"Prompt Baking","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2504.05321","title":"VALUE: Value-Aware Large Language Model for Query Rewriting via Weighted Trie in Sponsored Search","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2110.05702","title":"Auditing Robot Learning for Safety and Compliance during Deployment","created":"2021-10-12","cited_by_count":4,"area":null},{"id":"2407.13493","title":"Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2503.04969","title":"Data-Efficient Learning from Human Interventions for Mobile Robots","created":"2025-03-06","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":"2604.08553","title":"GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback","created":"2026-03-11","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":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2106.11345","title":"Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations","created":"2021-06-21","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":"2402.03040","title":"InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions","created":"2024-02-05","cited_by_count":3,"area":null},{"id":"2407.12061","title":"Situated Instruction Following","created":"2024-07-15","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":"2501.17899","title":"The Right to AI","created":"2025-01-29","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":"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":"2507.08249","title":"Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm","created":"2025-07-11","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}],"next_cursor":"100"}