{"list":"other","total":68,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"1802.08802","title":"Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration","created":"2018-02-24","cited_by_count":284},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277},{"id":"2303.09014","title":"ART: Automatic multi-step reasoning and tool-use for large language models","created":"2023-03-16","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":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2208.14271","title":"Faithful Reasoning Using Large Language Models","created":"2022-08-30","cited_by_count":130},{"id":"2209.07686","title":"Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango","created":"2022-09-16","cited_by_count":128},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"2202.08137","title":"A data-driven approach for learning to control computers","created":"2022-02-16","cited_by_count":88},{"id":"2301.12050","title":"Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling","created":"2023-01-28","cited_by_count":88},{"id":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","cited_by_count":84},{"id":"2210.01296","title":"Recitation-Augmented Language Models","created":"2022-10-04","cited_by_count":65},{"id":"2302.00763","title":"Collaborating with language models for embodied reasoning","created":"2023-02-01","cited_by_count":61},{"id":"1812.09195","title":"Learning to Navigate the Web","created":"2018-12-21","cited_by_count":60},{"id":"2301.04589","title":"Memory Augmented Large Language Models are Computationally Universal","created":"2023-01-10","cited_by_count":47},{"id":"2201.08896","title":"Environment Generation for Zero-Shot Compositional Reinforcement Learning","created":"2022-01-21","cited_by_count":32},{"id":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30},{"id":"2211.09935","title":"CAPE: Corrective Actions from Precondition Errors using Large Language Models","created":"2022-11-17","cited_by_count":30},{"id":"1902.07257","title":"DOM-Q-NET: Grounded RL on Structured Language","created":"2019-02-19","cited_by_count":25},{"id":"1808.09132","title":"Mapping Natural Language Commands to Web Elements","created":"2018-08-28","cited_by_count":23},{"id":"1602.02261","title":"End-to-End Goal-Driven Web Navigation","created":"2016-02-06","cited_by_count":10},{"id":"2203.07828","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","created":"2022-03-15","cited_by_count":5}],"next_cursor":null}