{"list":"other","total":68,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"2206.15000","title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","created":"2022-06-30","cited_by_count":218},{"id":"2006.08381","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","created":"2020-06-15","cited_by_count":161},{"id":"2005.10283","title":"Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation","created":"2020-05-20","cited_by_count":138},{"id":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138},{"id":"1803.00047","title":"Analyzing Uncertainty in Neural Machine Translation","created":"2018-02-28","cited_by_count":126},{"id":"2008.05122","title":"The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models","created":"2020-08-12","cited_by_count":125},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104},{"id":"2210.04714","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","created":"2022-10-10","cited_by_count":104},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102},{"id":"1703.01030","title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction","created":"2017-03-03","cited_by_count":93},{"id":"2210.14306","title":"Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming","created":"2022-10-25","cited_by_count":91},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84},{"id":"1606.07839","title":"Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles","created":"2016-06-24","cited_by_count":77},{"id":"1907.00208","title":"Deep Gamblers: Learning to Abstain with Portfolio Theory","created":"2019-06-29","cited_by_count":71},{"id":"1712.01818","title":"Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models","created":"2017-12-05","cited_by_count":68},{"id":"1806.07772","title":"Accurate and Diverse Sampling of Sequences based on a \"Best of Many\" Sample Objective","created":"2018-06-20","cited_by_count":56},{"id":"2105.08504","title":"Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation","created":"2021-05-18","cited_by_count":56},{"id":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55},{"id":"2202.04903","title":"Investigating Explainability of Generative AI for Code through Scenario-based Design","created":"2022-02-10","cited_by_count":47},{"id":"1902.06349","title":"Learning to Infer Program Sketches","created":"2019-02-17","cited_by_count":44},{"id":"2009.13267","title":"Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models","created":"2020-09-20","cited_by_count":44},{"id":"2104.03820","title":"Perfection Not Required? Human-AI Partnerships in Code Translation","created":"2021-04-08","cited_by_count":42},{"id":"1805.09461","title":"Deep Reinforcement Learning For Sequence to Sequence Models","created":"2018-05-24","cited_by_count":39},{"id":"1906.10816","title":"Program Synthesis and Semantic Parsing with Learned Code Idioms","created":"2019-06-26","cited_by_count":34},{"id":"1805.04604","title":"Confidence Modeling for Neural Semantic Parsing","created":"2018-05-11","cited_by_count":33},{"id":"2106.10158","title":"Learning to Complete Code with Sketches","created":"2021-06-18","cited_by_count":23},{"id":"1704.00559","title":"Neural Lattice-to-Sequence Models for Uncertain Inputs","created":"2017-04-03","cited_by_count":20},{"id":"1404.0417","title":"Mining Idioms from Source Code","created":"2014-04-01","cited_by_count":19},{"id":"2210.01964","title":"The Calibration Generalization Gap","created":"2022-10-05","cited_by_count":18},{"id":"2111.01582","title":"LMdiff: A Visual Diff Tool to Compare Language Models","created":"2021-11-02","cited_by_count":17},{"id":"1810.01398","title":"Optimal Completion Distillation for Sequence Learning","created":"2018-10-02","cited_by_count":14},{"id":"2208.14613","title":"How Readable is Model-generated Code? Examining Readability and Visual Inspection of GitHub Copilot","created":"2022-08-31","cited_by_count":14},{"id":"1804.07915","title":"A Stable and Effective Learning Strategy for Trainable Greedy Decoding","created":"2018-04-21","cited_by_count":12},{"id":"1411.1752","title":"Submodular meets Structured: Finding Diverse Subsets in Exponentially-Large Structured Item Sets","created":"2014-11-06","cited_by_count":11},{"id":"1609.07561","title":"Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser","created":"2016-09-24","cited_by_count":11},{"id":"1609.07730","title":"Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation","created":"2016-09-25","cited_by_count":11},{"id":"2008.10634","title":"DiverseNet: When One Right Answer is not Enough","created":"2020-08-24","cited_by_count":11},{"id":"1309.5655","title":"A new look at reweighted message passing","created":"2013-09-22","cited_by_count":9},{"id":"1405.5208","title":"A Tutorial on Dual Decomposition and Lagrangian Relaxation for Inference in Natural Language Processing","created":"2014-01-23","cited_by_count":8},{"id":"2009.00481","title":"Efficient Message Passing for 0-1 ILPs with Binary Decision Diagrams","created":"2020-09-01","cited_by_count":8},{"id":"2111.10270","title":"FastDOG: Fast Discrete Optimization on GPU","created":"2021-11-19","cited_by_count":8},{"id":"1612.05460","title":"A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems","created":"2016-12-16","cited_by_count":7},{"id":"1802.04544","title":"On the Relative Succinctness of Sentential Decision Diagrams","created":"2018-02-13","cited_by_count":6},{"id":"2011.14039","title":"An Investigation of Language Model Interpretability via Sentence Editing","created":"2020-11-28","cited_by_count":4},{"id":"1805.11224","title":"Distilling Knowledge for Search-based Structured Prediction","created":"2018-05-29","cited_by_count":3},{"id":"2201.11536","title":"Decision Diagrams for Discrete Optimization: A Survey of Recent Advances","created":"2022-01-27","cited_by_count":3},{"id":"2107.06402","title":"Mining Idioms in the Wild","created":"2021-07-13","cited_by_count":2}],"next_cursor":null}