{"total":52,"rows":[{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"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":"2405.00200","title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","created":"2024-04-30","cited_by_count":128,"area":null},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84,"area":null},{"id":"2401.06766","title":"Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements","created":"2024-01-12","cited_by_count":83,"area":null},{"id":"2212.06713","title":"Structured Prompting: Scaling In-Context Learning to 1,000 Examples","created":"2022-12-13","cited_by_count":81,"area":null},{"id":"2212.10947","title":"Parallel Context Windows for Large Language Models","created":"2022-12-21","cited_by_count":81,"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":"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":"2211.13892","title":"Complementary Explanations for Effective In-Context Learning","created":"2022-11-25","cited_by_count":71,"area":null},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38,"area":null},{"id":"2310.09139","title":"The Consensus Game: Language Model Generation via Equilibrium Search","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2405.20612","title":"UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation","created":"2024-05-31","cited_by_count":31,"area":null},{"id":"2405.02743","title":"Beyond Performance: Quantifying and Mitigating Label Bias in LLMs","created":"2024-05-04","cited_by_count":25,"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":"2310.10266","title":"Generative Calibration for In-context Learning","created":"2023-10-16","cited_by_count":20,"area":null},{"id":"2305.14926","title":"Universal Self-Adaptive Prompting","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2309.06991","title":"Unsupervised Contrast-Consistent Ranking with Language Models","created":"2023-09-13","cited_by_count":13,"area":null},{"id":"2503.08640","title":"Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2410.01288","title":"Mitigating Copy Bias in In-Context Learning through Neuron Pruning","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2411.02988","title":"Confidence Calibration of Classifiers with Many Classes","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2311.07115","title":"Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions","created":"2023-11-13","cited_by_count":9,"area":null},{"id":"2406.16535","title":"Token-based Decision Criteria Are Suboptimal in In-context Learning","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2505.13636","title":"Incentivizing Truthful Language Models via Peer Elicitation Games","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2509.03116","title":"Measuring Scalar Constructs in Social Science with LLMs","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2402.10353","title":"Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2411.02018","title":"Shortcut Learning in In-Context Learning: A Survey","created":"2024-11-04","cited_by_count":8,"area":null},{"id":"2212.08408","title":"Decoder Tuning: Efficient Language Understanding as Decoding","created":"2022-12-16","cited_by_count":6,"area":null},{"id":"2305.12749","title":"A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2407.00100","title":"Enhancing In-Context Learning via Implicit Demonstration Augmentation","created":"2024-06-27","cited_by_count":6,"area":null},{"id":"2408.11546","title":"Memorization in In-Context Learning","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2403.17552","title":"Naive Bayes-based Context Extension for Large Language Models","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2401.06877","title":"Promptly Predicting Structures: The Return of Inference","created":"2024-01-12","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":"2309.11506","title":"Matching Table Metadata with Business Glossaries Using Large Language Models","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2310.19572","title":"Improving Input-label Mapping with Demonstration Replay for In-context Learning","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2406.11115","title":"Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2501.15708","title":"StaICC: Standardized Evaluation for Classification Task in In-context Learning","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2505.01110","title":"MateICL: Mitigating Attention Dispersion in Large-Scale In-Context Learning","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2506.12796","title":"Surprise Calibration for Better In-Context Learning","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2511.14385","title":"Mitigating Label Length Bias in Large Language Models","created":"2025-11-18","cited_by_count":2,"area":null},{"id":"2502.04997","title":"Aligning Black-box Language Models with Human Judgments","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2505.23783","title":"Boosting In-Context Learning in LLMs Through the Lens of Classical Supervised Learning","created":"2025-05-22","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":"2401.09783","title":"Leveraging Biases in Large Language Models: \"bias-kNN'' for Effective Few-Shot Learning","created":"2024-01-18","cited_by_count":0,"area":null},{"id":"2410.18764","title":"Task Calibration: Calibrating Large Language Models on Inference Tasks","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2505.14233","title":"Mechanistic Fine-tuning for In-context Learning","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2512.12688","title":"How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2605.23180","title":"Self-Improving In-Context Learning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.30615","title":"Improving Selective Classification with Pairwise Queries for Binary Classification","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.07419","title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}