{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190},{"id":"2106.00737","title":"Implicit Representations of Meaning in Neural Language Models","created":"2021-06-01","cited_by_count":180},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"1611.06221","title":"Foundations of Structural Causal Models with Cycles and Latent Variables","created":"2016-11-18","cited_by_count":134},{"id":"2212.01681","title":"Language Models as Agent Models","created":"2022-12-03","cited_by_count":132},{"id":"1912.02875","title":"Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions","created":"2019-12-05","cited_by_count":125},{"id":"2211.09066","title":"Teaching Algorithmic Reasoning via In-context Learning","created":"2022-11-15","cited_by_count":112},{"id":"1912.02877","title":"Training Agents using Upside-Down Reinforcement Learning","created":"2019-12-05","cited_by_count":107},{"id":"2304.03843","title":"Why think step by step? Reasoning emerges from the locality of experience","created":"2023-04-07","cited_by_count":103},{"id":"2107.00793","title":"The Causal-Neural Connection: Expressiveness, Learnability, and Inference","created":"2021-07-02","cited_by_count":98},{"id":"1604.03670","title":"Interactive Perception: Leveraging Action in Perception and Perception in Action","created":"2016-04-13","cited_by_count":78},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75},{"id":"2204.04875","title":"Learning to Induce Causal Structure","created":"2022-04-11","cited_by_count":68},{"id":"1801.04016","title":"Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution","created":"2018-01-11","cited_by_count":66},{"id":"2110.10819","title":"Shaking the foundations: delusions in sequence models for interaction and control","created":"2021-10-20","cited_by_count":62},{"id":"1901.08162","title":"Causal Reasoning from Meta-reinforcement Learning","created":"2019-01-23","cited_by_count":53},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50},{"id":"2210.05675","title":"Transformers generalize differently from information stored in context vs in weights","created":"2022-10-11","cited_by_count":49},{"id":"2208.06267","title":"Causal Imitation Learning with Unobserved Confounders","created":"2022-08-12","cited_by_count":41},{"id":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","cited_by_count":36},{"id":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","cited_by_count":36},{"id":"1807.03024","title":"Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders","created":"2018-07-09","cited_by_count":35},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34},{"id":"1910.01751","title":"Causal Induction from Visual Observations for Goal Directed Tasks","created":"2019-10-03","cited_by_count":31},{"id":"2211.02763","title":"Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes","created":"2022-11-04","cited_by_count":30},{"id":"2102.07024","title":"Interactive Learning from Activity Description","created":"2021-02-13","cited_by_count":26},{"id":"2203.02336","title":"Differentiable Causal Discovery Under Latent Interventions","created":"2022-03-04","cited_by_count":21},{"id":"2206.08353","title":"Towards Understanding How Machines Can Learn Causal Overhypotheses","created":"2022-06-16","cited_by_count":14},{"id":"2202.11960","title":"All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL","created":"2022-02-24","cited_by_count":9},{"id":"2302.04250","title":"Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration","created":"2023-02-08","cited_by_count":2}],"next_cursor":null}