{"list":"other","total":86,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1604.04173","title":"Distribution-Free Predictive Inference For Regression","created":"2016-04-14","cited_by_count":668},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1904.06019","title":"Conformal Prediction Under Covariate Shift","created":"2019-04-12","cited_by_count":519},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"2106.00170","title":"Adaptive Conformal Inference Under Distribution Shift","created":"2021-06-01","cited_by_count":375},{"id":"2202.13415","title":"Conformal prediction beyond exchangeability","created":"2022-02-27","cited_by_count":355},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2208.02814","title":"Conformal Risk Control","created":"2022-08-04","cited_by_count":299},{"id":"2101.02703","title":"Distribution-Free, Risk-Controlling Prediction Sets","created":"2021-01-07","cited_by_count":288},{"id":"2110.01052","title":"Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control","created":"2021-10-03","cited_by_count":271},{"id":"1905.02928","title":"Predictive inference with the jackknife+","created":"2019-05-08","cited_by_count":211},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"1906.04908","title":"SPoC: Search-based Pseudocode to Code","created":"2019-06-12","cited_by_count":176},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2202.07282","title":"Adaptive Conformal Predictions for Time Series","created":"2022-02-15","cited_by_count":161},{"id":"2305.12616","title":"Conformal Prediction With Conditional Guarantees","created":"2023-05-22","cited_by_count":152},{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"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":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129},{"id":"2208.08401","title":"Conformal Inference for Online Prediction with Arbitrary Distribution Shifts","created":"2022-08-17","cited_by_count":128},{"id":"2004.07453","title":"The Right Tool for the Job: Matching Model and Instance Complexities","created":"2020-04-16","cited_by_count":126},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126},{"id":"1909.07889","title":"Distributional conformal prediction","created":"2019-09-17","cited_by_count":105},{"id":"2012.08668","title":"Mitigating Bias in Calibration Error Estimation","created":"2020-12-15","cited_by_count":101},{"id":"2103.03323","title":"Distribution-free uncertainty quantification for classification under label shift","created":"2021-03-04","cited_by_count":101},{"id":"2309.17249","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","created":"2023-09-29","cited_by_count":94},{"id":"2307.16895","title":"Conformal PID Control for Time Series Prediction","created":"2023-07-31","cited_by_count":88},{"id":"2008.04267","title":"Robust Validation: Confident Predictions Even When Distributions Shift","created":"2020-08-10","cited_by_count":82},{"id":"1811.07253","title":"Quantifying Uncertainties in Natural Language Processing Tasks","created":"2018-11-18","cited_by_count":79},{"id":"2104.08803","title":"Consistent Accelerated Inference via Confident Adaptive Transformers","created":"2021-04-18","cited_by_count":74},{"id":"2210.16133","title":"Stop Measuring Calibration When Humans Disagree","created":"2022-10-28","cited_by_count":71},{"id":"1802.06300","title":"Exact and Robust Conformal Inference Methods for Predictive Machine Learning With Dependent Data","created":"2018-02-17","cited_by_count":66},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55},{"id":"2211.07634","title":"Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding","created":"2022-11-14","cited_by_count":54},{"id":"2102.08898","title":"Few-shot Conformal Prediction with Auxiliary Tasks","created":"2021-02-17","cited_by_count":53},{"id":"2211.16886","title":"A Unifying Theory of Distance from Calibration","created":"2022-11-30","cited_by_count":53},{"id":"2205.00978","title":"Quality-Aware Decoding for Neural Machine Translation","created":"2022-05-02","cited_by_count":49},{"id":"2106.00394","title":"Improving Conditional Coverage via Orthogonal Quantile Regression","created":"2021-06-01","cited_by_count":48},{"id":"2306.04459","title":"Uncertainty in Natural Language Processing: Sources, Quantification, and Applications","created":"2023-06-05","cited_by_count":44},{"id":"1908.05428","title":"With Malice Towards None: Assessing Uncertainty via Equalized Coverage","created":"2019-08-15","cited_by_count":43},{"id":"2103.04044","title":"Putting Humans in the Natural Language Processing Loop: A Survey","created":"2021-03-06","cited_by_count":40},{"id":"1712.09089","title":"An Exact and Robust Conformal Inference Method for Counterfactual and Synthetic Controls","created":"2017-12-25","cited_by_count":36},{"id":"1805.09460","title":"Cautious Deep Learning","created":"2018-05-24","cited_by_count":35},{"id":"2109.06352","title":"Uncertainty-Aware Machine Translation Evaluation","created":"2021-09-13","cited_by_count":35},{"id":"2401.13744","title":"Conformal Prediction Sets Improve Human Decision Making","created":"2024-01-24","cited_by_count":35},{"id":"2305.02633","title":"Conformal Nucleus Sampling","created":"2023-05-04","cited_by_count":33},{"id":"2310.01262","title":"Non-Exchangeable Conformal Risk Control","created":"2023-10-02","cited_by_count":29},{"id":"2202.07650","title":"Conformal Prediction Sets with Limited False Positives","created":"2022-02-15","cited_by_count":28},{"id":"2111.02592","title":"Conformal prediction for text infilling and part-of-speech prediction","created":"2021-11-04","cited_by_count":22},{"id":"2210.07913","title":"Efficiently Controlling Multiple Risks with Pareto Testing","created":"2022-10-14","cited_by_count":22},{"id":"2402.00707","title":"Non-Exchangeable Conformal Language Generation with Nearest Neighbors","created":"2024-02-01","cited_by_count":21},{"id":"2311.13628","title":"Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models","created":"2023-11-22","cited_by_count":17},{"id":"2310.11430","title":"An Empirical Study of Translation Hypothesis Ensembling with Large Language Models","created":"2023-10-17","cited_by_count":16},{"id":"2402.16102","title":"Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?","created":"2024-02-25","cited_by_count":15},{"id":"2403.03868","title":"Confidence on the Focal: Conformal Prediction with Selection-Conditional Coverage","created":"2024-03-06","cited_by_count":14},{"id":"2310.09926","title":"Estimating Uncertainty in Multimodal Foundation Models using Public Internet Data","created":"2023-10-15","cited_by_count":10},{"id":"2204.06546","title":"Disentangling Uncertainty in Machine Translation Evaluation","created":"2022-04-13","cited_by_count":9},{"id":"2306.01549","title":"Evaluating Machine Translation Quality with Conformal Predictive Distributions","created":"2023-06-02","cited_by_count":9},{"id":"2205.10586","title":"Calibration of Natural Language Understanding Models with Venn--ABERS Predictors","created":"2022-05-21","cited_by_count":6},{"id":"2402.10046","title":"How Flawed Is ECE? An Analysis via Logit Smoothing","created":"2024-02-15","cited_by_count":6},{"id":"2306.06221","title":"Conformalizing Machine Translation Evaluation","created":"2023-06-09","cited_by_count":5},{"id":"2312.09304","title":"Well-calibrated Confidence Measures for Multi-label Text Classification with a Large Number of Labels","created":"2023-12-14","cited_by_count":5},{"id":"2203.11015","title":"Filter Drug-induced Liver Injury Literature with Natural Language Processing and Ensemble Learning","created":"2022-03-09","cited_by_count":4},{"id":"2306.03598","title":"CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models","created":"2023-06-06","cited_by_count":3},{"id":"2306.06642","title":"Well-Calibrated Probabilistic Predictive Maintenance using Venn-Abers","created":"2023-06-11","cited_by_count":3},{"id":"2309.07332","title":"Reliability-based cleaning of noisy training labels with inductive conformal prediction in multi-modal biomedical data mining","created":"2023-09-13","cited_by_count":3},{"id":"2210.12619","title":"Conformal Predictor for Improving Zero-shot Text Classification Efficiency","created":"2022-10-23","cited_by_count":2}],"next_cursor":null}