{"list":"other","total":60,"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1912.03817","title":"Machine Unlearning","created":"2019-12-09","cited_by_count":1061},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2103.09568","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","created":"2021-03-17","cited_by_count":256},{"id":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161},{"id":"2309.00667","title":"Taken out of context: On measuring situational awareness in LLMs","created":"2023-09-01","cited_by_count":143},{"id":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139},{"id":"2312.03664","title":"Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia","created":"2023-12-06","cited_by_count":126},{"id":"2305.17066","title":"Mindstorms in Natural Language-Based Societies of Mind","created":"2023-05-26","cited_by_count":107},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80},{"id":"1909.01496","title":"Neural Linguistic Steganography","created":"2019-09-03","cited_by_count":78},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75},{"id":"2310.18512","title":"Preventing Language Models From Hiding Their Reasoning","created":"2023-10-27","cited_by_count":65},{"id":"2402.04559","title":"Can Large Language Model Agents Simulate Human Trust Behavior?","created":"2024-02-07","cited_by_count":64},{"id":"2312.01037","title":"Eliciting Latent Knowledge from Quirky Language Models","created":"2023-12-02","cited_by_count":62},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60},{"id":"2312.06717","title":"Privacy Issues in Large Language Models: A Survey","created":"2023-12-11","cited_by_count":60},{"id":"2210.14889","title":"Perfectly Secure Steganography Using Minimum Entropy Coupling","created":"2022-10-24","cited_by_count":44},{"id":"2108.07790","title":"Mitigating harm in language models with conditional-likelihood filtration","created":"2021-08-04","cited_by_count":40},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40},{"id":"1810.11702","title":"Multi-Agent Common Knowledge Reinforcement Learning","created":"2018-10-27","cited_by_count":31},{"id":"2312.06677","title":"Intelligent Virtual Assistants with LLM-based Process Automation","created":"2023-12-04","cited_by_count":26},{"id":"2309.01660","title":"Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Brain","created":"2023-09-04","cited_by_count":18},{"id":"2210.12124","title":"Equivariant Networks for Zero-Shot Coordination","created":"2022-10-21","cited_by_count":16},{"id":"2307.05842","title":"The Butterfly Effect in Artificial Intelligence Systems: Implications for AI Bias and Fairness","created":"2023-07-11","cited_by_count":13},{"id":"2207.10170","title":"Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks","created":"2022-07-20","cited_by_count":12},{"id":"2107.08295","title":"Communicating via Markov Decision Processes","created":"2021-07-17","cited_by_count":10},{"id":"2202.07106","title":"Learning to Mitigate AI Collusion on Economic Platforms","created":"2022-02-15","cited_by_count":10},{"id":"2312.07779","title":"Tell, don't show: Declarative facts influence how LLMs generalize","created":"2023-12-12","cited_by_count":9},{"id":"2311.07815","title":"Cooperative AI via Decentralized Commitment Devices","created":"2023-11-14","cited_by_count":7},{"id":"1907.01886","title":"Recent Advances of Image Steganography with Generative Adversarial Networks","created":"2019-06-18","cited_by_count":5},{"id":"2008.07871","title":"Fast Agent-Based Simulation Framework with Applications to Reinforcement Learning and the Study of Trading Latency Effects","created":"2020-08-18","cited_by_count":5},{"id":"2206.12765","title":"Generalized Beliefs for Cooperative AI","created":"2022-06-26","cited_by_count":5},{"id":"2211.11043","title":"Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-Agent Reinforcement Learning","created":"2022-11-20","cited_by_count":4},{"id":"2303.10733","title":"Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning","created":"2023-03-19","cited_by_count":4},{"id":"1905.12432","title":"Hijacking Malaria Simulators with Probabilistic Programming","created":"2019-05-29","cited_by_count":3},{"id":"2110.04740","title":"Algorithmic collusion: A critical review","created":"2021-10-10","cited_by_count":3},{"id":"2011.06660","title":"Communication complexity of Nash equilibrium in potential games","created":"2020-11-12","cited_by_count":2}],"next_cursor":null}