{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2304.11477","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","created":"2023-04-22","cited_by_count":501},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2305.12295","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","created":"2023-05-20","cited_by_count":391},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2302.08399","title":"Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks","created":"2023-02-16","cited_by_count":292},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202},{"id":"2106.00737","title":"Implicit Representations of Meaning in Neural Language Models","created":"2021-06-01","cited_by_count":180},{"id":"2201.13360","title":"Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization","created":"2022-01-31","cited_by_count":178},{"id":"2212.07919","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","created":"2022-12-15","cited_by_count":177},{"id":"2006.08381","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","created":"2020-06-15","cited_by_count":161},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"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":"2303.06247","title":"Task and Motion Planning with Large Language Models for Object Rearrangement","created":"2023-03-10","cited_by_count":141},{"id":"2204.07931","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?","created":"2022-04-17","cited_by_count":138},{"id":"2302.05128","title":"Translating Natural Language to Planning Goals with Large-Language Models","created":"2023-02-10","cited_by_count":133},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","cited_by_count":114},{"id":"1606.03622","title":"Data Recombination for Neural Semantic Parsing","created":"2016-06-11","cited_by_count":111},{"id":"1805.04793","title":"Coarse-to-Fine Decoding for Neural Semantic Parsing","created":"2018-05-12","cited_by_count":110},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"2005.10636","title":"Graph-based, Self-Supervised Program Repair from Diagnostic Feedback","created":"2020-05-20","cited_by_count":94},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89},{"id":"2302.06706","title":"On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)","created":"2023-02-13","cited_by_count":85},{"id":"2210.05359","title":"Mind's Eye: Grounded Language Model Reasoning through Simulation","created":"2022-10-11","cited_by_count":84},{"id":"2204.13807","title":"A very preliminary analysis of DALL-E 2","created":"2022-04-25","cited_by_count":82},{"id":"2306.03081","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","created":"2023-06-05","cited_by_count":80},{"id":"2111.13654","title":"Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs","created":"2021-11-26","cited_by_count":79},{"id":"2208.00005","title":"Testing Relational Understanding in Text-Guided Image Generation","created":"2022-07-29","cited_by_count":59},{"id":"2205.05718","title":"Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks","created":"2022-05-11","cited_by_count":56},{"id":"2208.05446","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","created":"2022-08-10","cited_by_count":45},{"id":"2004.12169","title":"Learning to Update Natural Language Comments Based on Code Changes","created":"2020-04-25","cited_by_count":31},{"id":"2205.12374","title":"Learning to Model Editing Processes","created":"2022-05-24","cited_by_count":30},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22},{"id":"1404.0099","title":"Venture: a higher-order probabilistic programming platform with programmable inference","created":"2014-04-01","cited_by_count":20},{"id":"2006.00418","title":"Learning to refer informatively by amortizing pragmatic reasoning","created":"2020-05-31","cited_by_count":17},{"id":"2209.07662","title":"NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning","created":"2022-09-16","cited_by_count":16},{"id":"2305.01020","title":"Evaluating statistical language models as pragmatic reasoners","created":"2023-05-01","cited_by_count":15},{"id":"2302.06729","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","created":"2023-02-13","cited_by_count":13},{"id":"1812.01569","title":"Nested Reasoning About Autonomous Agents Using Probabilistic Programs","created":"2018-12-04","cited_by_count":7},{"id":"2209.07800","title":"The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding","created":"2022-09-16","cited_by_count":7},{"id":"2205.09735","title":"Foundation Posteriors for Approximate Probabilistic Inference","created":"2022-05-19","cited_by_count":6},{"id":"1704.04977","title":"Probabilistic programs for inferring the goals of autonomous agents","created":"2017-04-17","cited_by_count":4},{"id":"2102.12616","title":"Modular Object-Oriented Games: A Task Framework for Reinforcement Learning, Psychology, and Neuroscience","created":"2021-02-25","cited_by_count":4},{"id":"1805.04988","title":"Word learning and the acquisition of syntactic--semantic overhypotheses","created":"2018-05-14","cited_by_count":3},{"id":"1910.14124","title":"Bayesian causal inference via probabilistic program synthesis","created":"2019-10-30","cited_by_count":2},{"id":"2109.12296","title":"Jointly Learning to Repair Code and Generate Commit Message","created":"2021-09-25","cited_by_count":2}],"next_cursor":null}