{"list":"other","total":56,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"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":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"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":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"1604.04173","title":"Distribution-Free Predictive Inference For Regression","created":"2016-04-14","cited_by_count":668},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"1905.03222","title":"Conformalized Quantile Regression","created":"2019-05-08","cited_by_count":629},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"1904.06019","title":"Conformal Prediction Under Covariate Shift","created":"2019-04-12","cited_by_count":519},{"id":"2006.02544","title":"Classification with Valid and Adaptive Coverage","created":"2020-06-03","cited_by_count":396},{"id":"2106.00170","title":"Adaptive Conformal Inference Under Distribution Shift","created":"2021-06-01","cited_by_count":375},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2009.14193","title":"Uncertainty Sets for Image Classifiers using Conformal Prediction","created":"2020-09-29","cited_by_count":366},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"1909.00277","title":"Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning","created":"2019-08-31","cited_by_count":285},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"id":"1905.02928","title":"Predictive inference with the jackknife+","created":"2019-05-08","cited_by_count":211},{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2310.03094","title":"Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning","created":"2023-10-04","cited_by_count":143},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"id":"2104.08279","title":"Testing for Outliers with Conformal p-values","created":"2021-04-16","cited_by_count":134},{"id":"2402.10978","title":"Language Models with Conformal Factuality Guarantees","created":"2024-02-15","cited_by_count":131},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92},{"id":"2307.16895","title":"Conformal PID Control for Time Series Prediction","created":"2023-07-31","cited_by_count":88},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60},{"id":"2505.19970","title":"CP-Router: An Uncertainty-Aware Router Between LLM and LRM","created":"2025-05-26","cited_by_count":20},{"id":"2309.03797","title":"Conformal Autoregressive Generation: Beam Search with Coverage Guarantees","created":"2023-09-07","cited_by_count":16},{"id":"2511.07396","title":"C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning","created":"2025-11-10","cited_by_count":8}],"next_cursor":null}