{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"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":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2109.05093","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","created":"2021-09-10","cited_by_count":411},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"1611.01734","title":"Deep Biaffine Attention for Neural Dependency Parsing","created":"2016-11-06","cited_by_count":334},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"1909.05378","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","created":"2019-09-11","cited_by_count":185},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163},{"id":"2006.06264","title":"Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics","created":"2020-06-11","cited_by_count":158},{"id":"2010.12725","title":"Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?","created":"2020-10-24","cited_by_count":147},{"id":"2010.02840","title":"Semantic Evaluation for Text-to-SQL with Distilled Test Suites","created":"2020-10-06","cited_by_count":126},{"id":"2009.11423","title":"Task-Oriented Dialogue as Dataflow Synthesis","created":"2020-09-24","cited_by_count":122},{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118},{"id":"1810.07942","title":"Semantic Parsing for Task Oriented Dialog using Hierarchical Representations","created":"2018-10-18","cited_by_count":101},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89},{"id":"2211.02011","title":"Inverse scaling can become U-shaped","created":"2022-11-03","cited_by_count":76},{"id":"1903.00802","title":"Calibration of Encoder Decoder Models for Neural Machine Translation","created":"2019-03-03","cited_by_count":68},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66},{"id":"2005.00963","title":"On the Inference Calibration of Neural Machine Translation","created":"2020-05-03","cited_by_count":61},{"id":"1905.08704","title":"AMR Parsing as Sequence-to-Graph Transduction","created":"2019-05-21","cited_by_count":50},{"id":"2112.08696","title":"Few-Shot Semantic Parsing with Language Models Trained On Code","created":"2021-12-16","cited_by_count":50},{"id":"1910.05389","title":"Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study","created":"2019-10-11","cited_by_count":40},{"id":"2010.12770","title":"Conversational Semantic Parsing for Dialog State Tracking","created":"2020-10-24","cited_by_count":40},{"id":"2204.12793","title":"Modern Baselines for SPARQL Semantic Parsing","created":"2022-04-27","cited_by_count":34},{"id":"1805.04604","title":"Confidence Modeling for Neural Semantic Parsing","created":"2018-05-11","cited_by_count":33},{"id":"1909.02607","title":"Broad-Coverage Semantic Parsing as Transduction","created":"2019-09-05","cited_by_count":32},{"id":"2210.01964","title":"The Calibration Generalization Gap","created":"2022-10-05","cited_by_count":18},{"id":"2004.04361","title":"Calibrating Structured Output Predictors for Natural Language Processing","created":"2020-04-09","cited_by_count":17},{"id":"2110.00519","title":"Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images","created":"2021-10-01","cited_by_count":14},{"id":"1910.10138","title":"Universal Decompositional Semantic Parsing","created":"2019-10-22","cited_by_count":8},{"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":"2104.05696","title":"Joint Universal Syntactic and Semantic Parsing","created":"2021-04-12","cited_by_count":5},{"id":"2105.13496","title":"Diagnosing Transformers in Task-Oriented Semantic Parsing","created":"2021-05-27","cited_by_count":5},{"id":"2205.12228","title":"When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems","created":"2022-05-24","cited_by_count":2}],"next_cursor":null}