{"list":"other","total":52,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"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":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2006.02544","title":"Classification with Valid and Adaptive Coverage","created":"2020-06-03","cited_by_count":396},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"2009.14193","title":"Uncertainty Sets for Image Classifiers using Conformal Prediction","created":"2020-09-29","cited_by_count":366},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"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":"1609.00451","title":"Least Ambiguous Set-Valued Classifiers with Bounded Error Levels","created":"2016-09-02","cited_by_count":272},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2005.10608","title":"Unsupervised Quality Estimation for Neural Machine Translation","created":"2020-05-21","cited_by_count":211},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2007.08792","title":"Uncertainty Quantification and Deep Ensembles","created":"2020-07-17","cited_by_count":139},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"id":"2311.07383","title":"LM-Polygraph: Uncertainty Estimation for Language Models","created":"2023-11-13","cited_by_count":131},{"id":"2005.07972","title":"Conformal Prediction: a Unified Review of Theory and New Challenges","created":"2020-05-16","cited_by_count":118},{"id":"2310.09716","title":"Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting","created":"2023-10-15","cited_by_count":69},{"id":"2310.00741","title":"FELM: Benchmarking Factuality Evaluation of Large Language Models","created":"2023-10-01","cited_by_count":66},{"id":"2305.17564","title":"Federated Conformal Predictors for Distributed Uncertainty Quantification","created":"2023-05-27","cited_by_count":46},{"id":"2306.04459","title":"Uncertainty in Natural Language Processing: Sources, Quantification, and Applications","created":"2023-06-05","cited_by_count":44},{"id":"2305.02633","title":"Conformal Nucleus Sampling","created":"2023-05-04","cited_by_count":33},{"id":"2310.04782","title":"Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning","created":"2023-10-07","cited_by_count":29},{"id":"2311.07536","title":"A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering","created":"2023-11-13","cited_by_count":23},{"id":"2111.02592","title":"Conformal prediction for text infilling and part-of-speech prediction","created":"2021-11-04","cited_by_count":22},{"id":"2312.01714","title":"Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models","created":"2023-12-04","cited_by_count":18},{"id":"2401.08350","title":"Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models","created":"2024-01-16","cited_by_count":17},{"id":"2309.03797","title":"Conformal Autoregressive Generation: Beam Search with Coverage Guarantees","created":"2023-09-07","cited_by_count":16},{"id":"2311.09358","title":"Empirical evaluation of Uncertainty Quantification in Retrieval-Augmented Language Models for Science","created":"2023-11-15","cited_by_count":7}],"next_cursor":null}