{"list":"other","total":52,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2011.01403","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","created":"2020-11-03","cited_by_count":276},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2211.15006","title":"Fine-tuning language models to find agreement among humans with diverse preferences","created":"2022-11-28","cited_by_count":189},{"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":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173},{"id":"2301.04246","title":"Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations","created":"2023-01-10","cited_by_count":158},{"id":"2302.00560","title":"Co-Writing with Opinionated Language Models Affects Users' Views","created":"2023-02-01","cited_by_count":148},{"id":"2303.16755","title":"Training Language Models with Language Feedback at Scale","created":"2023-03-28","cited_by_count":128},{"id":"2305.13661","title":"On the Risk of Misinformation Pollution with Large Language Models","created":"2023-05-23","cited_by_count":128},{"id":"2406.07814","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","created":"2024-06-12","cited_by_count":123},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113},{"id":"2307.15810","title":"Understanding the Benefits and Challenges of Using Large Language Model-based Conversational Agents for Mental Well-being Support","created":"2023-07-28","cited_by_count":75},{"id":"2305.17008","title":"NormBank: A Knowledge Bank of Situational Social Norms","created":"2023-05-26","cited_by_count":60},{"id":"2311.10766","title":"Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values","created":"2023-11-15","cited_by_count":50},{"id":"2402.05699","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","created":"2024-02-08","cited_by_count":46},{"id":"2309.01291","title":"Generative Social Choice","created":"2023-09-03","cited_by_count":43},{"id":"2404.03502","title":"AI and the Problem of Knowledge Collapse","created":"2024-04-04","cited_by_count":34},{"id":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27},{"id":"2309.05958","title":"The Moral Machine Experiment on Large Language Models","created":"2023-09-12","cited_by_count":25},{"id":"2312.15907","title":"Align on the Fly: Adapting Chatbot Behavior to Established Norms","created":"2023-12-26","cited_by_count":23},{"id":"2302.01339","title":"Creating a Large Language Model of a Philosopher","created":"2023-02-02","cited_by_count":21},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13},{"id":"2305.05364","title":"Large Language Model Programs","created":"2023-05-09","cited_by_count":11},{"id":"2403.12862","title":"Epistemology of Language Models: Do Language Models Have Holistic Knowledge?","created":"2024-03-19","cited_by_count":9},{"id":"1812.00879","title":"Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks","created":"2018-11-30","cited_by_count":7},{"id":"2305.17147","title":"Heterogeneous Value Alignment Evaluation for Large Language Models","created":"2023-05-26","cited_by_count":7},{"id":"2405.09794","title":"Human-AI Safety: A Descendant of Generative AI and Control Systems Safety","created":"2024-05-16","cited_by_count":7},{"id":"2404.04516","title":"Language Models as Critical Thinking Tools: A Case Study of Philosophers","created":"2024-04-06","cited_by_count":6}],"next_cursor":null}