{"list":"other","total":53,"rows":[{"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"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":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"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":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1912.02781","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","created":"2019-12-05","cited_by_count":901},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"1911.11132","title":"Scaling Out-of-Distribution Detection for Real-World Settings","created":"2019-11-25","cited_by_count":465},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301},{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217},{"id":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"1902.06977","title":"Evaluating model calibration in classification","created":"2019-02-19","cited_by_count":168},{"id":"1303.4402","title":"From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews","created":"2013-03-18","cited_by_count":108},{"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":"2210.10683","title":"Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP","created":"2022-10-19","cited_by_count":102},{"id":"2006.12800","title":"Calibration of Neural Networks using Splines","created":"2020-06-23","cited_by_count":97},{"id":"2110.13771","title":"AugMax: Adversarial Composition of Random Augmentations for Robust Training","created":"2021-10-26","cited_by_count":90},{"id":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76},{"id":"2206.08514","title":"A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks","created":"2022-06-17","cited_by_count":74},{"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":"2012.15349","title":"DynaSent: A Dynamic Benchmark for Sentiment Analysis","created":"2020-12-30","cited_by_count":63},{"id":"1906.01181","title":"Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations","created":"2019-06-04","cited_by_count":61},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34},{"id":"2110.15317","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","created":"2021-10-28","cited_by_count":28},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25},{"id":"1912.02990","title":"SemEval-2014 Task 9: Sentiment Analysis in Twitter","created":"2019-12-06","cited_by_count":20},{"id":"2110.07586","title":"Can Explanations Be Useful for Calibrating Black Box Models?","created":"2021-10-14","cited_by_count":20},{"id":"2010.11506","title":"Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data","created":"2020-10-22","cited_by_count":17},{"id":"2110.07159","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","created":"2021-10-14","cited_by_count":17}],"next_cursor":null}