{"total":852,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901,"area":"lr"},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812,"area":"alignment"},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"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":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2103.12051","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","created":"2021-03-22","cited_by_count":264,"area":null},{"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":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"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":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2107.11277","title":"Machine Learning with a Reject Option: A survey","created":"2021-07-23","cited_by_count":109,"area":null},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105,"area":null},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2405.16908","title":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","created":"2024-05-27","cited_by_count":87,"area":null},{"id":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81,"area":null},{"id":"2104.08803","title":"Consistent Accelerated Inference via Confident Adaptive Transformers","created":"2021-04-18","cited_by_count":74,"area":null},{"id":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72,"area":null},{"id":"2301.06197","title":"Who Should Predict? Exact Algorithms For Learning to Defer to Humans","created":"2023-01-15","cited_by_count":70,"area":null},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67,"area":null},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66,"area":null},{"id":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","cited_by_count":66,"area":null},{"id":"2101.12523","title":"Optimal strategies for reject option classifiers","created":"2021-01-29","cited_by_count":61,"area":null},{"id":"2206.06640","title":"Confidence Score for Source-Free Unsupervised Domain Adaptation","created":"2022-06-14","cited_by_count":59,"area":null},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59,"area":null},{"id":"2108.11035","title":"NGC: A Unified Framework for Learning with Open-World Noisy Data","created":"2021-08-25","cited_by_count":58,"area":null},{"id":"2404.10960","title":"Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations","created":"2024-04-16","cited_by_count":54,"area":null},{"id":"2405.10301","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","created":"2024-05-16","cited_by_count":54,"area":"alignment"},{"id":"2501.19306","title":"SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling","created":"2025-01-31","cited_by_count":54,"area":"lr"},{"id":"2106.02395","title":"DOCTOR: A Simple Method for Detecting Misclassification Errors","created":"2021-06-04","cited_by_count":53,"area":null},{"id":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52,"area":null},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2310.11689","title":"Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs","created":"2023-10-18","cited_by_count":50,"area":null},{"id":"2207.09584","title":"Sample Efficient Learning of Predictors that Complement Humans","created":"2022-07-19","cited_by_count":46,"area":null},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"area":null},{"id":"2311.08877","title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation","created":"2023-11-15","cited_by_count":39,"area":null},{"id":"2303.17093","title":"OpenMix: Exploring Outlier Samples for Misclassification Detection","created":"2023-03-30","cited_by_count":38,"area":null},{"id":"2407.01032","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","created":"2024-07-01","cited_by_count":37,"area":null},{"id":"2310.14772","title":"Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms","created":"2023-10-23","cited_by_count":36,"area":null},{"id":"2112.06751","title":"Role of Human-AI Interaction in Selective Prediction","created":"2021-12-13","cited_by_count":35,"area":null},{"id":"2302.11874","title":"What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers","created":"2023-02-23","cited_by_count":35,"area":null},{"id":"2110.15403","title":"Selective Regression Under Fairness Criteria","created":"2021-10-28","cited_by_count":34,"area":null},{"id":"2105.04290","title":"Meta-Cal: Well-controlled Post-hoc Calibration by Ranking","created":"2021-05-10","cited_by_count":33,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2207.13048","title":"Domain Adaptation under Open Set Label Shift","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2404.10193","title":"Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering","created":"2024-04-16","cited_by_count":32,"area":"mllm"},{"id":"2305.03236","title":"A Survey on Out-of-Distribution Detection in NLP","created":"2023-05-05","cited_by_count":31,"area":null},{"id":"2609.26550","title":"JEV-as-a-Judge: Accept When Confident, Escalate When Unsure","created":"2026-09-22","cited_by_count":30,"area":"lr"},{"id":"2305.13282","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","created":"2023-05-22","cited_by_count":29,"area":null},{"id":"2202.07650","title":"Conformal Prediction Sets with Limited False Positives","created":"2022-02-15","cited_by_count":28,"area":null},{"id":"2402.10727","title":"From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation","created":"2024-02-16","cited_by_count":28,"area":null},{"id":"2207.07506","title":"Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2306.03009","title":"Using Sequences of Life-events to Predict Human Lives","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2407.13732","title":"Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer","created":"2024-07-18","cited_by_count":26,"area":null},{"id":"2409.11884","title":"Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances","created":"2024-09-18","cited_by_count":26,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2109.00893","title":"A Survey on Open Set Recognition","created":"2021-08-18","cited_by_count":25,"area":null},{"id":"2206.09034","title":"Towards Better Selective Classification","created":"2022-06-17","cited_by_count":25,"area":null},{"id":"2306.08751","title":"Improving Selective Visual Question Answering by Learning from Your Peers","created":"2023-06-14","cited_by_count":25,"area":null},{"id":"2202.05613","title":"CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning","created":"2022-02-11","cited_by_count":24,"area":null},{"id":"2202.07603","title":"Fairness Indicators for Systematic Assessments of Visual Feature Extractors","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2306.08328","title":"Distribution Shift Inversion for Out-of-Distribution Prediction","created":"2023-06-14","cited_by_count":23,"area":null},{"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":"2203.11027","title":"Reasoning over Public and Private Data in Retrieval-Based Systems","created":"2022-03-14","cited_by_count":21,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","cited_by_count":21,"area":"alignment"},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"id":"2106.02248","title":"Knowing the No-match: Entity Alignment with Dangling Cases","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","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":"2110.13741","title":"Disrupting Deep Uncertainty Estimation Without Harming Accuracy","created":"2021-10-26","cited_by_count":19,"area":null},{"id":"2112.00337","title":"A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks","created":"2021-12-01","cited_by_count":19,"area":null},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2204.07309","title":"Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale","created":"2022-04-15","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":"2401.03482","title":"Uncertainty Quantification on Clinical Trial Outcome Prediction","created":"2024-01-07","cited_by_count":19,"area":null},{"id":"2401.04695","title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","created":"2024-01-09","cited_by_count":18,"area":null},{"id":"2101.08732","title":"Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning","created":"2021-01-21","cited_by_count":17,"area":null},{"id":"2410.15729","title":"A Two-Stage Learning-to-Defer Approach for Multi-Task Learning","created":"2024-10-21","cited_by_count":17,"area":null},{"id":"2502.13962","title":"Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering","created":"2025-02-19","cited_by_count":17,"area":"lr"},{"id":"2303.08010","title":"Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models","created":"2023-03-14","cited_by_count":16,"area":"inference"},{"id":"2305.15508","title":"How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2311.15451","title":"Uncertainty-aware Language Modeling for Selective Question Answering","created":"2023-11-26","cited_by_count":16,"area":null},{"id":"2406.01806","title":"Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation","created":"2024-06-03","cited_by_count":16,"area":null},{"id":"2411.00299","title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","created":"2024-11-01","cited_by_count":16,"area":"mllm"},{"id":"2502.01027","title":"Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees","created":"2025-02-03","cited_by_count":16,"area":null},{"id":"2506.20650","title":"Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer","created":"2025-06-25","cited_by_count":16,"area":null},{"id":"2206.07609","title":"Epistemic Deep Learning","created":"2022-06-15","cited_by_count":15,"area":null},{"id":"2301.01054","title":"Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise","created":"2023-01-03","cited_by_count":15,"area":null},{"id":"2307.09254","title":"Selective Generation for Controllable Language Models","created":"2023-07-18","cited_by_count":15,"area":null},{"id":"2405.21028","title":"LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models","created":"2024-05-31","cited_by_count":15,"area":null},{"id":"2410.15361","title":"A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators","created":"2024-10-20","cited_by_count":15,"area":null},{"id":"2105.14785","title":"Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart","created":"2021-05-31","cited_by_count":14,"area":null},{"id":"2302.03679","title":"How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2303.12317","title":"Re-thinking Federated Active Learning based on Inter-class Diversity","created":"2023-03-22","cited_by_count":14,"area":null},{"id":"2304.06701","title":"Learning Personalized Decision Support Policies","created":"2023-04-13","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":"2406.04370","title":"Large Language Model Confidence Estimation via Black-Box Access","created":"2024-06-01","cited_by_count":14,"area":null}],"next_cursor":"100"}