{"total":30,"rows":[{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392,"area":null},{"id":"2304.10428","title":"GPT-NER: Named Entity Recognition via Large Language Models","created":"2023-04-20","cited_by_count":160,"area":null},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115,"area":null},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111,"area":null},{"id":"2112.01589","title":"InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation","created":"2021-12-02","cited_by_count":33,"area":null},{"id":"2311.09627","title":"Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination","created":"2023-11-16","cited_by_count":23,"area":null},{"id":"2311.04128","title":"Generative learning for nonlinear dynamics","created":"2023-11-07","cited_by_count":22,"area":null},{"id":"2312.04021","title":"A Study on the Calibration of In-context Learning","created":"2023-12-07","cited_by_count":22,"area":null},{"id":"2307.03749","title":"On the Efficacy of Sampling Adapters","created":"2023-07-07","cited_by_count":17,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2504.09096","title":"High dimensional online calibration in polynomial time","created":"2025-04-12","cited_by_count":13,"area":null},{"id":"2202.12226","title":"Probing BERT's priors with serial reproduction chains","created":"2022-02-24","cited_by_count":11,"area":null},{"id":"2102.13189","title":"Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data","created":"2021-02-25","cited_by_count":8,"area":null},{"id":"2310.01041","title":"Language Model Decoding as Direct Metrics Optimization","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2411.02603","title":"FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees","created":"2024-11-04","cited_by_count":7,"area":null},{"id":"2505.19060","title":"UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models","created":"2025-05-25","cited_by_count":5,"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":"2511.11966","title":"On the Entropy Calibration of Language Models","created":"2025-11-15","cited_by_count":4,"area":null},{"id":"2409.19984","title":"CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Models","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2603.12248","title":"Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models","created":"2026-03-12","cited_by_count":3,"area":null},{"id":"2307.06713","title":"Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models","created":"2023-07-13","cited_by_count":1,"area":null},{"id":"2605.00062","title":"RETO: A Rotary-Enhanced Transformer Operator for High-Fidelity Prediction of Automotive Aerodynamics","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.24850","title":"Repeated Sequences Reveal Gaps between Large Language Models and Natural Language","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2209.13636","title":"Local Grammar-Based Coding Revisited","created":"2022-09-27","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":"2402.17601","title":"Advancing sleep detection by modelling weak label sets: A novel weakly supervised learning approach","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2511.21753","title":"Extracting Disaster Impacts and Impact Related Locations in Social Media Posts Using Large Language Models","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2604.03589","title":"Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.30981","title":"Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.23130","title":"Identification and Honest Recovery from Semantic Observation Kernels: Operator Error, Coarsening, and Stability","created":"2026-07-25","cited_by_count":0,"area":null}],"next_cursor":null}