{"total":68,"rows":[{"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":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161,"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":"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":"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":"2305.14613","title":"Selectively Answering Ambiguous Questions","created":"2023-05-24","cited_by_count":66,"area":null},{"id":"2108.04718","title":"Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation","created":"2021-08-10","cited_by_count":65,"area":null},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2105.08504","title":"Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation","created":"2021-05-18","cited_by_count":56,"area":null},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47,"area":null},{"id":"2206.02757","title":"Robust Calibration with Multi-domain Temperature Scaling","created":"2022-06-06","cited_by_count":39,"area":null},{"id":"2112.07184","title":"Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation","created":"2021-12-14","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":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"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":"2104.08676","title":"Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning","created":"2021-04-18","cited_by_count":31,"area":null},{"id":"2203.07559","title":"On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency","created":"2022-03-14","cited_by_count":31,"area":null},{"id":"2305.03236","title":"A Survey on Out-of-Distribution Detection in NLP","created":"2023-05-05","cited_by_count":31,"area":null},{"id":"2105.14556","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","created":"2021-05-30","cited_by_count":25,"area":null},{"id":"2410.01380","title":"Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2504.20168","title":"MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools","created":"2025-04-28","cited_by_count":15,"area":"agents"},{"id":"2211.06862","title":"WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation","created":"2022-11-13","cited_by_count":13,"area":null},{"id":"2103.10291","title":"Smoothing and Shrinking the Sparse Seq2Seq Search Space","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2203.10623","title":"Calibration of Machine Reading Systems at Scale","created":"2022-03-20","cited_by_count":11,"area":null},{"id":"2305.07021","title":"Simple Token-Level Confidence Improves Caption Correctness","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2107.10427","title":"Confidence-Aware Scheduled Sampling for Neural Machine Translation","created":"2021-07-22","cited_by_count":10,"area":null},{"id":"2108.12731","title":"$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection","created":"2021-08-29","cited_by_count":10,"area":null},{"id":"2205.00704","title":"Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES","created":"2022-05-02","cited_by_count":10,"area":null},{"id":"2411.09661","title":"Adaptive Decoding via Latent Preference Optimization","created":"2024-11-14","cited_by_count":10,"area":"alignment"},{"id":"2105.15087","title":"Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation","created":"2021-05-31","cited_by_count":9,"area":null},{"id":"2204.00471","title":"Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models","created":"2022-04-01","cited_by_count":9,"area":null},{"id":"2205.09665","title":"Automated Crossword Solving","created":"2022-05-19","cited_by_count":9,"area":null},{"id":"2305.00593","title":"Reliable Gradient-free and Likelihood-free Prompt Tuning","created":"2023-04-30","cited_by_count":8,"area":null},{"id":"2308.15141","title":"Uncertainty Aware Training to Improve Deep Learning Model Calibration for Classification of Cardiac MR Images","created":"2023-08-29","cited_by_count":7,"area":null},{"id":"2411.16742","title":"Text-to-SQL Calibration: No Need to Ask -- Just Rescale Model Probabilities","created":"2024-11-23","cited_by_count":7,"area":null},{"id":"2405.15458","title":"FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler","created":"2024-05-24","cited_by_count":6,"area":null},{"id":"2303.06946","title":"Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2505.23804","title":"Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2109.06253","title":"Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2210.12427","title":"Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model","created":"2022-10-22","cited_by_count":4,"area":"distill"},{"id":"2212.04205","title":"DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2402.17527","title":"Predict the Next Word: Humans exhibit uncertainty in this task and language models _____","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2506.00637","title":"Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristics","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2305.05098","title":"Who Needs Decoders? Efficient Estimation of Sequence-level Attributes","created":"2023-05-09","cited_by_count":3,"area":null},{"id":"2306.04176","title":"When to Read Documents or QA History: On Unified and Selective Open-domain QA","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2509.16696","title":"Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2102.08424","title":"Searching for Search Errors in Neural Morphological Inflection","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2203.11413","title":"Learning Confidence for Transformer-based Neural Machine Translation","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2211.10193","title":"Layer-Stack Temperature Scaling","created":"2022-11-18","cited_by_count":2,"area":null},{"id":"2412.15683","title":"Variability Need Not Imply Error: The Case of Adequate but Semantically Distinct Responses","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2504.19044","title":"Calibrating Translation Decoding with Quality Estimation on LLMs","created":"2025-04-26","cited_by_count":2,"area":null},{"id":"2305.19498","title":"Perception and Semantic Aware Regularization for Sequential Confidence Calibration","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2311.03672","title":"CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2405.06487","title":"Improving Deep Learning Model Calibration for Cardiac Applications using Deterministic Uncertainty Networks and Uncertainty-aware Training","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2409.17046","title":"Detecting Temporal Ambiguity in Questions","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2606.17234","title":"Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2210.13082","title":"Are Deep Sequence Classifiers Good at Non-Trivial Generalization?","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2302.12367","title":"Extracting Victim Counts from Text","created":"2023-02-23","cited_by_count":0,"area":null},{"id":"2304.13883","title":"Neural Keyphrase Generation: Analysis and Evaluation","created":"2023-04-27","cited_by_count":0,"area":null},{"id":"2308.03429","title":"RCMHA: Relative Convolutional Multi-Head Attention for Natural Language Modelling","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2503.01195","title":"PostHoc FREE Calibrating on Kolmogorov Arnold Networks","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2604.08974","title":"Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.20490","title":"ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2610.02612","title":"Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}