{"list":"other","total":74,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"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":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"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":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"1402.4102","title":"Stochastic Gradient Hamiltonian Monte Carlo","created":"2014-02-17","cited_by_count":343},{"id":"2110.01052","title":"Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control","created":"2021-10-03","cited_by_count":271},{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2211.15006","title":"Fine-tuning language models to find agreement among humans with diverse preferences","created":"2022-11-28","cited_by_count":189},{"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":"1306.6430","title":"A General Framework for Updating Belief Distributions","created":"2013-06-27","cited_by_count":175},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"2102.06571","title":"Bayesian Neural Network Priors Revisited","created":"2021-02-12","cited_by_count":121},{"id":"2006.14768","title":"Deep Partition Aggregation: Provable Defense against General Poisoning Attacks","created":"2020-06-26","cited_by_count":115},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115},{"id":"2007.01162","title":"Tilted Empirical Risk Minimization","created":"2020-07-02","cited_by_count":106},{"id":"1602.02311","title":"R\\'enyi Divergence Variational Inference","created":"2016-02-06","cited_by_count":104},{"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":"1412.3730","title":"Inconsistency of Bayesian Inference for Misspecified Linear Models, and a Proposal for Repairing It","created":"2014-12-11","cited_by_count":95},{"id":"2008.04495","title":"Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks","created":"2020-08-11","cited_by_count":94},{"id":"1912.00894","title":"On the geometry of Stein variational gradient descent","created":"2019-12-02","cited_by_count":82},{"id":"2404.11599","title":"Variational Bayesian Last Layers","created":"2024-04-17","cited_by_count":69},{"id":"2402.00809","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","created":"2024-02-01","cited_by_count":62},{"id":"1812.03973","title":"Bayesian Layers: A Module for Neural Network Uncertainty","created":"2018-12-10","cited_by_count":57},{"id":"2202.02628","title":"Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation","created":"2022-02-05","cited_by_count":52},{"id":"2010.10604","title":"Bayesian Attention Modules","created":"2020-10-20","cited_by_count":51},{"id":"1503.08329","title":"Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm","created":"2015-03-28","cited_by_count":50},{"id":"1511.03243","title":"Black-box $\\alpha$-divergence Minimization","created":"2015-11-10","cited_by_count":37},{"id":"2305.15027","title":"A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods","created":"2023-05-24","cited_by_count":32},{"id":"1703.02914","title":"Dropout Inference in Bayesian Neural Networks with Alpha-divergences","created":"2017-03-08","cited_by_count":28},{"id":"2210.12642","title":"Accelerated Linearized Laplace Approximation for Bayesian Deep Learning","created":"2022-10-23","cited_by_count":28},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25},{"id":"2305.16597","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","created":"2023-05-26","cited_by_count":25},{"id":"2102.04754","title":"Bayesian Transformer Language Models for Speech Recognition","created":"2021-02-09","cited_by_count":22},{"id":"2405.03425","title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","created":"2024-05-06","cited_by_count":20},{"id":"2302.02300","title":"Run-Off Election: Improved Provable Defense against Data Poisoning Attacks","created":"2023-02-05","cited_by_count":17},{"id":"2305.12086","title":"Prefix Propagation: Parameter-Efficient Tuning for Long Sequences","created":"2023-05-20","cited_by_count":15},{"id":"2106.13624","title":"Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote","created":"2021-06-25","cited_by_count":13},{"id":"2110.04020","title":"Pathologies in priors and inference for Bayesian transformers","created":"2021-10-08","cited_by_count":13},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12},{"id":"2405.16246","title":"Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation","created":"2024-05-25","cited_by_count":9},{"id":"2203.09381","title":"Direct Gibbs posterior inference on risk minimizers: construction, concentration, and calibration","created":"2022-03-17","cited_by_count":7},{"id":"2502.11617","title":"In-Context Parametric Inference: Point or Distribution Estimators?","created":"2025-02-17","cited_by_count":4},{"id":"2410.14843","title":"Predictive variational inference: Learn the predictively optimal posterior distribution","created":"2024-10-18","cited_by_count":3},{"id":"2512.01667","title":"Detecting Model Misspecification in Bayesian Inverse Problems via Variational Gradient Descent","created":"2025-12-01","cited_by_count":3},{"id":"2510.01915","title":"Predictively Oriented Posteriors","created":"2025-10-02","cited_by_count":2}],"next_cursor":null}