{"total":390,"rows":[{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856,"area":"lr"},{"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":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783,"area":"lr"},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2110.06207","title":"Open-Set Recognition: a Good Closed-Set Classifier is All You Need?","created":"2021-10-12","cited_by_count":353,"area":null},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230,"area":null},{"id":"2209.09858","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","created":"2022-09-20","cited_by_count":212,"area":null},{"id":"2304.11633","title":"Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness","created":"2023-04-23","cited_by_count":130,"area":null},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126,"area":null},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"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":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2302.13439","title":"Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models","created":"2023-02-26","cited_by_count":91,"area":null},{"id":"2403.14119","title":"C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion","created":"2024-03-21","cited_by_count":83,"area":"mllm"},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79,"area":null},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75,"area":null},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2211.14293","title":"RbA: Segmenting Unknown Regions Rejected by All","created":"2022-11-25","cited_by_count":67,"area":null},{"id":"2203.07835","title":"Better Uncertainty Calibration via Proper Scores for Classification and Beyond","created":"2022-03-15","cited_by_count":65,"area":null},{"id":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63,"area":null},{"id":"2210.03736","title":"Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis","created":"2022-10-05","cited_by_count":63,"area":null},{"id":"2309.12236","title":"Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing","created":"2023-09-21","cited_by_count":63,"area":null},{"id":"2402.11457","title":"When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation","created":"2024-02-18","cited_by_count":59,"area":null},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57,"area":null},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"area":null},{"id":"2211.16886","title":"A Unifying Theory of Distance from Calibration","created":"2022-11-30","cited_by_count":53,"area":null},{"id":"2405.01976","title":"Conformal Prediction for Natural Language Processing: A Survey","created":"2024-05-03","cited_by_count":53,"area":null},{"id":"2203.13834","title":"A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration","created":"2022-03-25","cited_by_count":49,"area":null},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49,"area":null},{"id":"2305.13264","title":"Prompting is not a substitute for probability measurements in large language models","created":"2023-05-22","cited_by_count":44,"area":null},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"area":null},{"id":"2404.17287","title":"When to Trust LLMs: Aligning Confidence with Response Quality","created":"2024-04-26","cited_by_count":43,"area":null},{"id":"2206.02757","title":"Robust Calibration with Multi-domain Temperature Scaling","created":"2022-06-06","cited_by_count":39,"area":null},{"id":"2207.02238","title":"Improving Trustworthiness of AI Disease Severity Rating in Medical Imaging with Ordinal Conformal Prediction Sets","created":"2022-07-05","cited_by_count":38,"area":null},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38,"area":"mllm"},{"id":"2305.18764","title":"When Does Optimizing a Proper Loss Yield Calibration?","created":"2023-05-30","cited_by_count":36,"area":null},{"id":"2311.01723","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","created":"2023-11-03","cited_by_count":35,"area":"mllm"},{"id":"2401.13744","title":"Conformal Prediction Sets Improve Human Decision Making","created":"2024-01-24","cited_by_count":35,"area":null},{"id":"2207.11347","title":"An Impartial Take to the CNN vs Transformer Robustness Contest","created":"2022-07-22","cited_by_count":34,"area":null},{"id":"2210.00173","title":"Predictive Inference with Feature Conformal Prediction","created":"2022-10-01","cited_by_count":34,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2211.07443","title":"Calibrated Interpretation: Confidence Estimation in Semantic Parsing","created":"2022-11-14","cited_by_count":33,"area":null},{"id":"2210.16315","title":"Beyond calibration: estimating the grouping loss of modern neural networks","created":"2022-10-28","cited_by_count":32,"area":null},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32,"area":null},{"id":"2106.09613","title":"Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error","created":"2021-06-17","cited_by_count":29,"area":null},{"id":"2301.12618","title":"ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning","created":"2023-01-30","cited_by_count":28,"area":null},{"id":"2306.02738","title":"A Large-Scale Study of Probabilistic Calibration in Neural Network Regression","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2206.09034","title":"Towards Better Selective Classification","created":"2022-06-17","cited_by_count":25,"area":null},{"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,"area":null},{"id":"2212.12053","title":"On Calibrating Semantic Segmentation Models: Analyses and An Algorithm","created":"2022-12-22","cited_by_count":25,"area":null},{"id":"2403.19137","title":"CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models","created":"2024-03-28","cited_by_count":25,"area":"mllm"},{"id":"2208.00461","title":"Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks","created":"2022-07-31","cited_by_count":24,"area":null},{"id":"2409.19375","title":"DOTA: Distributional Test-Time Adaptation of Vision-Language Models","created":"2024-09-28","cited_by_count":23,"area":"mllm"},{"id":"2410.10414","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","created":"2024-10-14","cited_by_count":23,"area":"safety"},{"id":"2206.05833","title":"COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition","created":"2022-06-12","cited_by_count":22,"area":null},{"id":"2208.06164","title":"Joint Optimization of Ranking and Calibration with Contextualized Hybrid Model","created":"2022-08-12","cited_by_count":22,"area":null},{"id":"2302.01094","title":"Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation","created":"2023-02-02","cited_by_count":22,"area":null},{"id":"2404.18279","title":"Out-of-distribution Detection in Medical Image Analysis: A survey","created":"2024-04-28","cited_by_count":22,"area":null},{"id":"2402.07417","title":"An Empirical Study Into What Matters for Calibrating Vision-Language Models","created":"2024-02-12","cited_by_count":20,"area":"mllm"},{"id":"2503.02863","title":"SteerConf: Steering LLMs for Confidence Elicitation","created":"2025-03-04","cited_by_count":20,"area":null},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","cited_by_count":20,"area":null},{"id":"2107.13098","title":"A Tale Of Two Long Tails","created":"2021-07-27","cited_by_count":19,"area":null},{"id":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19,"area":null},{"id":"2304.09424","title":"Loss Minimization Yields Multicalibration for Large Neural Networks","created":"2023-04-19","cited_by_count":19,"area":null},{"id":"2307.05772","title":"Random-Set Neural Networks (RS-NN)","created":"2023-07-11","cited_by_count":19,"area":null},{"id":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","cited_by_count":19,"area":null},{"id":"2509.14034","title":"Enhancing Multi-Agent Debate System Performance via Confidence Expression","created":"2025-09-17","cited_by_count":19,"area":"agents"},{"id":"2210.01964","title":"The Calibration Generalization Gap","created":"2022-10-05","cited_by_count":18,"area":null},{"id":"2306.04590","title":"Proximity-Informed Calibration for Deep Neural Networks","created":"2023-06-07","cited_by_count":18,"area":null},{"id":"2406.06487","title":"When is Multicalibration Post-Processing Necessary?","created":"2024-06-10","cited_by_count":18,"area":null},{"id":"2303.12748","title":"Enabling Calibration In The Zero-Shot Inference of Large Vision-Language Models","created":"2023-03-11","cited_by_count":17,"area":"mllm"},{"id":"2306.01265","title":"Calibrating Multimodal Learning","created":"2023-06-02","cited_by_count":17,"area":null},{"id":"2501.19195","title":"Rethinking Early Stopping: Refine, Then Calibrate","created":"2025-01-31","cited_by_count":17,"area":null},{"id":"2303.11298","title":"Reliability in Semantic Segmentation: Are We on the Right Track?","created":"2023-03-20","cited_by_count":16,"area":null},{"id":"2307.07102","title":"Achelous: A Fast Unified Water-surface Panoptic Perception Framework based on Fusion of Monocular Camera and 4D mmWave Radar","created":"2023-07-14","cited_by_count":16,"area":null},{"id":"2405.04278","title":"Uncertainty Quantification Metrics for Deep Regression","created":"2024-05-07","cited_by_count":16,"area":null},{"id":"2308.11911","title":"ACLS: Adaptive and Conditional Label Smoothing for Network Calibration","created":"2023-08-23","cited_by_count":15,"area":null},{"id":"2310.09163","title":"Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN","created":"2023-10-13","cited_by_count":15,"area":null},{"id":"2402.04655","title":"Open-Vocabulary Calibration for Fine-tuned CLIP","created":"2024-02-07","cited_by_count":15,"area":"mllm"},{"id":"2111.10734","title":"Deep Probability Estimation","created":"2021-11-21","cited_by_count":14,"area":null},{"id":"2302.05118","title":"Beyond In-Domain Scenarios: Robust Density-Aware Calibration","created":"2023-02-10","cited_by_count":14,"area":null},{"id":"2306.01710","title":"A Data-Driven Measure of Relative Uncertainty for Misclassification Detection","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2311.11837","title":"Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms","created":"2023-11-20","cited_by_count":14,"area":null},{"id":"2211.15088","title":"Class Adaptive Network Calibration","created":"2022-11-28","cited_by_count":13,"area":null},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2412.12151","title":"SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration","created":"2024-12-11","cited_by_count":13,"area":"agents"},{"id":"2504.09096","title":"High dimensional online calibration in polynomial time","created":"2025-04-12","cited_by_count":13,"area":null},{"id":"2205.09968","title":"A General Framework for quantifying Aleatoric and Epistemic uncertainty in Graph Neural Networks","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2302.06495","title":"Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2308.14815","title":"Distributionally Robust Statistical Verification with Imprecise Neural Networks","created":"2023-08-28","cited_by_count":12,"area":null},{"id":"2408.02841","title":"Evaluating Posterior Probabilities: Decision Theory, Proper Scoring Rules, and Calibration","created":"2024-08-05","cited_by_count":12,"area":null},{"id":"2409.06424","title":"A Likelihood Ratio-Based Approach to Segmenting Unknown Objects","created":"2024-09-10","cited_by_count":12,"area":null},{"id":"2507.17383","title":"Confidence Calibration in Vision-Language-Action Models","created":"2025-07-23","cited_by_count":12,"area":"vla"},{"id":"2206.08222","title":"Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency","created":"2022-06-16","cited_by_count":11,"area":null},{"id":"2209.03580","title":"Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Survey","created":"2022-09-08","cited_by_count":11,"area":null}],"next_cursor":"100"}