{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"2403.13793","title":"Evaluating Frontier Models for Dangerous Capabilities","created":"2024-03-20","cited_by_count":128},{"id":"1912.01683","title":"Optimal Policies Tend to Seek Power","created":"2019-12-03","cited_by_count":119},{"id":"1711.09883","title":"AI Safety Gridworlds","created":"2017-11-27","cited_by_count":110},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105},{"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":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83},{"id":"2402.18225","title":"CogBench: a large language model walks into a psychology lab","created":"2024-02-28","cited_by_count":63},{"id":"2401.02843","title":"Thousands of AI Authors on the Future of AI","created":"2024-01-05","cited_by_count":48},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47},{"id":"2311.16093","title":"Visual cognition in multimodal large language models","created":"2023-11-27","cited_by_count":38},{"id":"2206.11349","title":"Prompt Injection: Parameterization of Fixed Inputs","created":"2022-05-31","cited_by_count":36},{"id":"2006.04948","title":"AI Research Considerations for Human Existential Safety (ARCHES)","created":"2020-05-30","cited_by_count":33},{"id":"2305.07153","title":"Towards best practices in AGI safety and governance: A survey of expert opinion","created":"2023-05-11","cited_by_count":27},{"id":"2310.16379","title":"Evaluating General-Purpose AI with Psychometrics","created":"2023-10-25","cited_by_count":23},{"id":"2404.16047","title":"From \"AI\" to Probabilistic Automation: How Does Anthropomorphization of Technical Systems Descriptions Influence Trust?","created":"2024-04-08","cited_by_count":18},{"id":"1805.12387","title":"Agents and Devices: A Relative Definition of Agency","created":"2018-05-31","cited_by_count":16},{"id":"2309.11975","title":"Inferring Capabilities from Task Performance with Bayesian Triangulation","created":"2023-09-21","cited_by_count":13},{"id":"2405.08989","title":"What is it for a Machine Learning Model to Have a Capability?","created":"2024-05-14","cited_by_count":10}],"next_cursor":null}