{"list":"other","total":69,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"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":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"2007.06823","title":"Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users","created":"2020-07-14","cited_by_count":338},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"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":"1905.00076","title":"Ensemble Distribution Distillation","created":"2019-04-30","cited_by_count":158},{"id":"1906.02506","title":"Practical Deep Learning with Bayesian Principles","created":"2019-06-06","cited_by_count":158},{"id":"1806.04854","title":"Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam","created":"2018-06-13","cited_by_count":131},{"id":"2102.06571","title":"Bayesian Neural Network Priors Revisited","created":"2021-02-12","cited_by_count":121},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","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":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101},{"id":"1907.07504","title":"Subspace Inference for Bayesian Deep Learning","created":"2019-07-17","cited_by_count":95},{"id":"2007.05864","title":"Bayesian Deep Ensembles via the Neural Tangent Kernel","created":"2020-07-11","cited_by_count":90},{"id":"1906.01930","title":"Approximate Inference Turns Deep Networks into Gaussian Processes","created":"2019-06-05","cited_by_count":89},{"id":"2002.05551","title":"PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees","created":"2020-02-13","cited_by_count":85},{"id":"2306.07967","title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","created":"2023-06-13","cited_by_count":85},{"id":"1603.04733","title":"Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors","created":"2016-03-15","cited_by_count":82},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67},{"id":"2203.07835","title":"Better Uncertainty Calibration via Proper Scores for Classification and Beyond","created":"2022-03-15","cited_by_count":65},{"id":"1812.03973","title":"Bayesian Layers: A Module for Neural Network Uncertainty","created":"2018-12-10","cited_by_count":57},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42},{"id":"1902.09754","title":"Function Space Particle Optimization for Bayesian Neural Networks","created":"2019-02-26","cited_by_count":41},{"id":"2203.07472","title":"Uncertainty Estimation for Language Reward Models","created":"2022-03-14","cited_by_count":37},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37},{"id":"2106.05586","title":"Data augmentation in Bayesian neural networks and the cold posterior effect","created":"2021-06-10","cited_by_count":36},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34},{"id":"2102.01691","title":"Exact Langevin Dynamics with Stochastic Gradients","created":"2021-02-02","cited_by_count":30},{"id":"2305.19249","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","created":"2023-05-30","cited_by_count":29},{"id":"2102.04754","title":"Bayesian Transformer Language Models for Speech Recognition","created":"2021-02-09","cited_by_count":22},{"id":"2106.07512","title":"Last Layer Marginal Likelihood for Invariance Learning","created":"2021-06-14","cited_by_count":21},{"id":"2106.10760","title":"On Stein Variational Neural Network Ensembles","created":"2021-06-20","cited_by_count":21},{"id":"2303.02444","title":"Calibrating Transformers via Sparse Gaussian Processes","created":"2023-03-04","cited_by_count":21},{"id":"2105.06964","title":"BNNpriors: A library for Bayesian neural network inference with different prior distributions","created":"2021-05-14","cited_by_count":20},{"id":"2306.12306","title":"Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift","created":"2023-06-21","cited_by_count":20},{"id":"2202.12439","title":"Learning Invariant Weights in Neural Networks","created":"2022-02-25","cited_by_count":16},{"id":"2110.04020","title":"Pathologies in priors and inference for Bayesian transformers","created":"2021-10-08","cited_by_count":13},{"id":"2110.08388","title":"Probing as Quantifying Inductive Bias","created":"2021-10-15","cited_by_count":12},{"id":"2304.01762","title":"Incorporating Unlabelled Data into Bayesian Neural Networks","created":"2023-04-04","cited_by_count":9},{"id":"2204.01334","title":"Efficient, Uncertainty-based Moderation of Neural Networks Text Classifiers","created":"2022-04-04","cited_by_count":7}],"next_cursor":null}