{"list":"other","total":79,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2002.06278","title":"Algorithmic Recourse: from Counterfactual Explanations to Interventions","created":"2020-02-14","cited_by_count":250},{"id":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229},{"id":"2202.07785","title":"Predictability and Surprise in Large Generative Models","created":"2022-02-15","cited_by_count":210},{"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},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"1906.09208","title":"Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices","created":"2019-06-21","cited_by_count":174},{"id":"2309.00236","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","created":"2023-09-01","cited_by_count":172},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2310.18940","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game","created":"2023-10-29","cited_by_count":152},{"id":"2302.00560","title":"Co-Writing with Opinionated Language Models Affects Users' Views","created":"2023-02-01","cited_by_count":148},{"id":"2210.05791","title":"Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction","created":"2022-10-11","cited_by_count":138},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"2312.04724","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","created":"2023-12-07","cited_by_count":138},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135},{"id":"2304.05332","title":"Emergent autonomous scientific research capabilities of large language models","created":"2023-04-11","cited_by_count":132},{"id":"2312.07913","title":"A Survey of Text Watermarking in the Era of Large Language Models","created":"2023-12-13","cited_by_count":112},{"id":"2310.08118","title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?","created":"2023-10-12","cited_by_count":108},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98},{"id":"2312.11671","title":"Evaluating Language-Model Agents on Realistic Autonomous Tasks","created":"2023-12-18","cited_by_count":96},{"id":"2211.13972","title":"Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?","created":"2022-11-25","cited_by_count":91},{"id":"2206.09511","title":"The Fallacy of AI Functionality","created":"2022-06-20","cited_by_count":88},{"id":"2311.04378","title":"Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models","created":"2023-11-07","cited_by_count":87},{"id":"2206.04737","title":"Outsider Oversight: Designing a Third Party Audit Ecosystem for AI Governance","created":"2022-06-09","cited_by_count":67},{"id":"2310.18512","title":"Preventing Language Models From Hiding Their Reasoning","created":"2023-10-27","cited_by_count":65},{"id":"2302.04844","title":"The Gradient of Generative AI Release: Methods and Considerations","created":"2023-02-05","cited_by_count":63},{"id":"2202.05338","title":"Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning","created":"2022-02-10","cited_by_count":48},{"id":"2311.10538","title":"Testing Language Model Agents Safely in the Wild","created":"2023-11-17","cited_by_count":46},{"id":"2306.13952","title":"Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools","created":"2023-06-24","cited_by_count":45},{"id":"2109.05067","title":"The Flaws of Policies Requiring Human Oversight of Government Algorithms","created":"2021-09-10","cited_by_count":44},{"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},{"id":"2306.03809","title":"Can large language models democratize access to dual-use biotechnology?","created":"2023-06-06","cited_by_count":35},{"id":"2303.15772","title":"Ecosystem Graphs: The Social Footprint of Foundation Models","created":"2023-03-28","cited_by_count":32},{"id":"2305.16941","title":"Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media","created":"2023-05-26","cited_by_count":30},{"id":"2303.12642","title":"Democratising AI: Multiple Meanings, Goals, and Methods","created":"2023-03-22","cited_by_count":29},{"id":"2208.08345","title":"Discovering Agents","created":"2022-08-17","cited_by_count":28},{"id":"2312.07413","title":"AI capabilities can be significantly improved without expensive retraining","created":"2023-12-12","cited_by_count":28},{"id":"2210.03535","title":"From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML","created":"2022-10-06","cited_by_count":27},{"id":"2306.06924","title":"TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI","created":"2023-06-12","cited_by_count":26},{"id":"2107.09287","title":"Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography","created":"2021-07-20","cited_by_count":24},{"id":"2303.16200","title":"Natural Selection Favors AIs over Humans","created":"2023-03-28","cited_by_count":24},{"id":"2401.08315","title":"Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening","created":"2024-01-16","cited_by_count":24},{"id":"2307.08823","title":"Risk assessment at AGI companies: A review of popular risk assessment techniques from other safety-critical industries","created":"2023-07-17","cited_by_count":19},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18},{"id":"2305.04699","title":"Runtime Monitoring of Dynamic Fairness Properties","created":"2023-05-08","cited_by_count":17},{"id":"2111.05969","title":"PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems","created":"2021-11-10","cited_by_count":16},{"id":"2302.00672","title":"'Generative CI' through Collective Response Systems","created":"2023-02-01","cited_by_count":13},{"id":"2310.13625","title":"Oversight for Frontier AI through a Know-Your-Customer Scheme for Compute Providers","created":"2023-10-20","cited_by_count":13},{"id":"2305.19861","title":"Human Control: Definitions and Algorithms","created":"2023-05-31","cited_by_count":10},{"id":"2206.02868","title":"A Human-Centric Take on Model Monitoring","created":"2022-06-06","cited_by_count":9},{"id":"2310.00328","title":"Deployment Corrections: An incident response framework for frontier AI models","created":"2023-09-30","cited_by_count":9},{"id":"2303.11074","title":"Generative AI and the Digital Commons","created":"2023-03-20","cited_by_count":8},{"id":"2205.15258","title":"Transparency, Governance and Regulation of Algorithmic Tools Deployed in the Criminal Justice System: a UK Case Study","created":"2022-05-30","cited_by_count":7},{"id":"2303.09001","title":"Reclaiming the Digital Commons: A Public Data Trust for Training Data","created":"2023-03-16","cited_by_count":7},{"id":"2001.09723","title":"Monitoring Misuse for Accountable 'Artificial Intelligence as a Service'","created":"2020-01-14","cited_by_count":6},{"id":"2205.15406","title":"From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse","created":"2022-05-30","cited_by_count":6},{"id":"2303.08956","title":"Exploring the Relevance of Data Privacy-Enhancing Technologies for AI Governance Use Cases","created":"2023-03-15","cited_by_count":6},{"id":"2110.04740","title":"Algorithmic collusion: A critical review","created":"2021-10-10","cited_by_count":3},{"id":"1812.08014","title":"Intelligent Autonomous Agents are Key to Cyber Defense of the Future Army Networks","created":"2018-12-18","cited_by_count":2}],"next_cursor":null}