{"list":"other","total":96,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2304.11477","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","created":"2023-04-22","cited_by_count":501},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302},{"id":"2208.04024","title":"Social Simulacra: Creating Populated Prototypes for Social Computing Systems","created":"2022-08-08","cited_by_count":301},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"2305.17144","title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","created":"2023-05-25","cited_by_count":289},{"id":"2304.07590","title":"Self-collaboration Code Generation via ChatGPT","created":"2023-04-15","cited_by_count":258},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250},{"id":"2309.04658","title":"Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf","created":"2023-09-09","cited_by_count":241},{"id":"2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","created":"2022-12-19","cited_by_count":240},{"id":"1808.00033","title":"Techniques for Interpretable Machine Learning","created":"2018-07-31","cited_by_count":238},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2307.14984","title":"S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents","created":"2023-07-27","cited_by_count":233},{"id":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202},{"id":"2205.12255","title":"TALM: Tool Augmented Language Models","created":"2022-05-24","cited_by_count":197},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187},{"id":"1612.07182","title":"Multi-Agent Cooperation and the Emergence of (Natural) Language","created":"2016-12-21","cited_by_count":185},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"2207.07051","title":"Language models show human-like content effects on reasoning tasks","created":"2022-07-14","cited_by_count":173},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"2307.00184","title":"Personality Traits in Large Language Models","created":"2023-07-01","cited_by_count":169},{"id":"2205.00445","title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","created":"2022-05-01","cited_by_count":156},{"id":"2307.11760","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","created":"2023-07-14","cited_by_count":146},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"2304.05332","title":"Emergent autonomous scientific research capabilities of large language models","created":"2023-04-11","cited_by_count":132},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114},{"id":"2305.13711","title":"LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models","created":"2023-05-23","cited_by_count":101},{"id":"2306.00924","title":"Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker","created":"2023-06-01","cited_by_count":95},{"id":"2308.04026","title":"AgentSims: An Open-Source Sandbox for Large Language Model Evaluation","created":"2023-08-08","cited_by_count":88},{"id":"2304.10436","title":"Safety Assessment of Chinese Large Language Models","created":"2023-04-20","cited_by_count":85},{"id":"2308.05960","title":"BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents","created":"2023-08-11","cited_by_count":84},{"id":"1805.10000","title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","created":"2018-05-25","cited_by_count":80},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78},{"id":"2004.13332","title":"The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies","created":"2020-04-28","cited_by_count":75},{"id":"2303.17220","title":"Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys","created":"2023-03-30","cited_by_count":75},{"id":"1804.09299","title":"Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models","created":"2018-04-25","cited_by_count":69},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66},{"id":"2003.10014","title":"Reinforcement Learning in Economics and Finance","created":"2020-03-22","cited_by_count":58},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42},{"id":"1809.01587","title":"GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation","created":"2018-09-05","cited_by_count":41},{"id":"1604.00545","title":"The AGI Containment Problem","created":"2016-04-02","cited_by_count":36},{"id":"2310.08367","title":"MCU: An Evaluation Framework for Open-Ended Game Agents","created":"2023-10-12","cited_by_count":34},{"id":"2304.10750","title":"Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback","created":"2023-04-21","cited_by_count":32},{"id":"2305.12487","title":"Augmenting Autotelic Agents with Large Language Models","created":"2023-05-21","cited_by_count":30},{"id":"2308.04030","title":"Gentopia: A Collaborative Platform for Tool-Augmented LLMs","created":"2023-08-08","cited_by_count":26},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25},{"id":"2305.07970","title":"The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?","created":"2023-05-13","cited_by_count":22},{"id":"2308.03313","title":"Quantifying the Impact of Large Language Models on Collective Opinion Dynamics","created":"2023-08-07","cited_by_count":22},{"id":"2308.00245","title":"The Hitchhiker's Guide to Program Analysis: A Journey with Large Language Models","created":"2023-08-01","cited_by_count":18},{"id":"2308.01423","title":"ChatMOF: An Autonomous AI System for Predicting and Generating Metal-Organic Frameworks","created":"2023-08-01","cited_by_count":17},{"id":"2311.08732","title":"Enhancing Emergency Decision-making with Knowledge Graphs and Large Language Models","created":"2023-11-15","cited_by_count":12},{"id":"1903.00402","title":"Machine learning in policy evaluation: new tools for causal inference","created":"2019-03-01","cited_by_count":10},{"id":"2108.09400","title":"Regression Discontinuity Designs","created":"2021-08-20","cited_by_count":5},{"id":"1611.07454","title":"An Agent-Based Model of Message Propagation in the Facebook Electronic Social Network","created":"2016-11-22","cited_by_count":3},{"id":"2304.08497","title":"Agent-Based Modeling and its Tradeoffs: An Introduction & Examples","created":"2023-04-06","cited_by_count":1}],"next_cursor":null}