{"total":3926,"rows":[{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795,"area":null},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"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,"area":null},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974,"area":null},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819,"area":null},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600,"area":null},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486,"area":null},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390,"area":null},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"area":null},{"id":"2110.00218","title":"On the Importance of Gradients for Detecting Distributional Shifts in the Wild","created":"2021-10-01","cited_by_count":339,"area":null},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308,"area":null},{"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,"area":null},{"id":"2202.01197","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","created":"2022-02-02","cited_by_count":300,"area":null},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2106.03004","title":"Exploring the Limits of Out-of-Distribution Detection","created":"2021-06-06","cited_by_count":283,"area":null},{"id":"2210.07242","title":"OpenOOD: Benchmarking Generalized Out-of-Distribution Detection","created":"2022-10-13","cited_by_count":268,"area":null},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266,"area":"offlinerl"},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2206.08129","title":"Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline","created":"2022-06-16","cited_by_count":248,"area":"driving"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2105.01879","title":"MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space","created":"2021-05-05","cited_by_count":233,"area":null},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231,"area":"alignment"},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224,"area":"wm"},{"id":"2308.05732","title":"PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers","created":"2023-08-10","cited_by_count":216,"area":"diffusion"},{"id":"2209.09858","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","created":"2022-09-20","cited_by_count":212,"area":null},{"id":"2102.11582","title":"Deep Deterministic Uncertainty: A Simple Baseline","created":"2021-02-23","cited_by_count":200,"area":null},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200,"area":"alignment"},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2103.15025","title":"On Hallucination and Predictive Uncertainty in Conditional Language Generation","created":"2021-03-28","cited_by_count":176,"area":null},{"id":"2203.04115","title":"Biological Sequence Design with GFlowNets","created":"2022-03-02","cited_by_count":174,"area":null},{"id":"2204.11423","title":"Trusted Multi-View Classification with Dynamic Evidential Fusion","created":"2022-04-25","cited_by_count":168,"area":null},{"id":"2111.09805","title":"DICE: Leveraging Sparsification for Out-of-Distribution Detection","created":"2021-11-18","cited_by_count":166,"area":null},{"id":"2403.04696","title":"Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification","created":"2024-03-07","cited_by_count":162,"area":null},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159,"area":null},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151,"area":null},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150,"area":null},{"id":"2307.01379","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","created":"2023-07-03","cited_by_count":150,"area":null},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146,"area":null},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"area":null},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131,"area":"wm"},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131,"area":null},{"id":"2303.02966","title":"Non-Parametric Outlier Synthesis","created":"2023-03-06","cited_by_count":129,"area":null},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2209.03302","title":"Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?","created":"2022-09-07","cited_by_count":125,"area":null},{"id":"2308.16175","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","created":"2023-08-30","cited_by_count":122,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120,"area":null},{"id":"2203.09168","title":"On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks","created":"2022-03-17","cited_by_count":120,"area":null},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120,"area":null},{"id":"2106.13799","title":"Assessing Generalization of SGD via Disagreement","created":"2021-06-25","cited_by_count":117,"area":null},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116,"area":null},{"id":"2109.09881","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","created":"2021-09-20","cited_by_count":116,"area":null},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115,"area":null},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114,"area":null},{"id":"2410.24210","title":"TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling","created":"2024-10-31","cited_by_count":113,"area":null},{"id":"2103.05445","title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","created":"2021-03-09","cited_by_count":109,"area":null},{"id":"2109.09960","title":"Mutual Consistency Learning for Semi-supervised Medical Image Segmentation","created":"2021-09-21","cited_by_count":108,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2202.05265","title":"Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging","created":"2022-02-10","cited_by_count":107,"area":null},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106,"area":null},{"id":"2102.08501","title":"DEUP: Direct Epistemic Uncertainty Prediction","created":"2021-02-16","cited_by_count":104,"area":null},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104,"area":null},{"id":"2210.04714","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","created":"2022-10-10","cited_by_count":104,"area":null},{"id":"2206.07275","title":"CARD: Classification and Regression Diffusion Models","created":"2022-06-15","cited_by_count":103,"area":"diffusion"},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2107.07455","title":"Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks","created":"2021-07-15","cited_by_count":101,"area":null},{"id":"1807.08364","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","created":"2018-07-22","cited_by_count":100,"area":"offlinerl"},{"id":"2109.14162","title":"Can multi-label classification networks know what they don't know?","created":"2021-09-29","cited_by_count":100,"area":null},{"id":"2311.06750","title":"Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark","created":"2023-11-12","cited_by_count":99,"area":null},{"id":"2208.05516","title":"Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP","created":"2022-08-10","cited_by_count":97,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2102.02051","title":"Trusted Multi-View Classification","created":"2021-02-03","cited_by_count":94,"area":null},{"id":"2104.14726","title":"MOOD: Multi-level Out-of-distribution Detection","created":"2021-04-30","cited_by_count":94,"area":null},{"id":"2108.00106","title":"Soft Calibration Objectives for Neural Networks","created":"2021-07-30","cited_by_count":92,"area":null},{"id":"2206.06602","title":"Deep Isolation Forest for Anomaly Detection","created":"2022-06-14","cited_by_count":92,"area":null},{"id":"2111.15430","title":"The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration","created":"2021-11-30","cited_by_count":91,"area":null},{"id":"2204.08322","title":"A high-resolution canopy height model of the Earth","created":"2022-04-13","cited_by_count":91,"area":null},{"id":"2309.03185","title":"Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields","created":"2023-09-06","cited_by_count":91,"area":null}],"next_cursor":"100"}