{"list":"other","total":54,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"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},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"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},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95},{"id":"2503.05777","title":"Medical Hallucinations in Foundation Models and Their Impact on Healthcare","created":"2025-02-26","cited_by_count":93},{"id":"2403.01216","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","created":"2024-03-02","cited_by_count":69},{"id":"2403.02509","title":"SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models","created":"2024-03-04","cited_by_count":56},{"id":"2405.10301","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","created":"2024-05-16","cited_by_count":54},{"id":"2503.02623","title":"Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models","created":"2025-03-04","cited_by_count":52},{"id":"2411.00784","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","created":"2024-10-17","cited_by_count":39},{"id":"2401.00211","title":"Open-TI: Open Traffic Intelligence with Augmented Language Model","created":"2023-12-30","cited_by_count":38},{"id":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35},{"id":"2502.04964","title":"Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistency","created":"2025-02-07","cited_by_count":30},{"id":"1612.08388","title":"Clustering Algorithms: A Comparative Approach","created":"2016-12-26","cited_by_count":28},{"id":"2506.00245","title":"Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity","created":"2025-05-30","cited_by_count":28},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27},{"id":"2410.14582","title":"Do LLMs estimate uncertainty well in instruction-following?","created":"2024-10-18","cited_by_count":26},{"id":"2502.17026","title":"Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology","created":"2025-02-24","cited_by_count":25},{"id":"2407.00994","title":"LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation","created":"2024-07-01","cited_by_count":23},{"id":"2504.13677","title":"Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results","created":"2025-04-18","cited_by_count":21},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21},{"id":"2502.16820","title":"Uncertainty Quantification of Large Language Models through Multi-Dimensional Responses","created":"2025-02-24","cited_by_count":18},{"id":"2508.14496","title":"Semantic Energy: Detecting LLM Hallucination Beyond Entropy","created":"2025-08-20","cited_by_count":18},{"id":"2311.15451","title":"Uncertainty-aware Language Modeling for Selective Question Answering","created":"2023-11-26","cited_by_count":16},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14},{"id":"2502.18389","title":"Monte Carlo Temperature: a robust sampling strategy for LLM's uncertainty quantification methods","created":"2025-02-25","cited_by_count":12},{"id":"2509.14478","title":"Estimating Semantic Alphabet Size for LLM Uncertainty Quantification","created":"2025-09-17","cited_by_count":8},{"id":"2511.16275","title":"SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory","created":"2025-11-20","cited_by_count":7},{"id":"2604.08708","title":"Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition","created":"2026-04-09","cited_by_count":7},{"id":"2410.20199","title":"Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models","created":"2024-10-26","cited_by_count":6},{"id":"2506.09684","title":"Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models","created":"2025-06-11","cited_by_count":6},{"id":"2502.14268","title":"MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels","created":"2025-02-20","cited_by_count":4},{"id":"2601.17329","title":"Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment","created":"2026-01-24","cited_by_count":4},{"id":"2509.07925","title":"GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models","created":"2025-09-09","cited_by_count":3},{"id":"2405.01978","title":"Quantifying Distribution Shifts and Uncertainties for Enhanced Model Robustness in Machine Learning Applications","created":"2024-05-03","cited_by_count":2},{"id":"2506.07446","title":"Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification","created":"2025-06-09","cited_by_count":2},{"id":"2603.20161","title":"Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models","created":"2026-03-20","cited_by_count":1}],"next_cursor":null}