{"list":"other","total":54,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225},{"id":"1906.10742","title":"Machine Learning Testing: Survey, Landscapes and Horizons","created":"2019-06-19","cited_by_count":218},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144},{"id":"2004.02990","title":"Evaluating the Evaluation of Diversity in Natural Language Generation","created":"2020-04-06","cited_by_count":129},{"id":"1904.02792","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","created":"2019-04-04","cited_by_count":127},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126},{"id":"1606.04316","title":"Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis","created":"2016-06-14","cited_by_count":93},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","cited_by_count":71},{"id":"1904.03971","title":"Jointly Measuring Diversity and Quality in Text Generation Models","created":"2019-04-08","cited_by_count":61},{"id":"2110.12773","title":"Scientific Machine Learning Benchmarks","created":"2021-10-25","cited_by_count":60},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54},{"id":"2302.09656","title":"Credal Bayesian Deep Learning","created":"2023-02-19","cited_by_count":45},{"id":"1903.05499","title":"DeepOBS: A Deep Learning Optimizer Benchmark Suite","created":"2019-03-13","cited_by_count":37},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36},{"id":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28},{"id":"2407.14614","title":"Evaluating language models as risk scores","created":"2024-07-19","cited_by_count":27},{"id":"2407.18698","title":"Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation","created":"2024-07-26","cited_by_count":27},{"id":"2410.06097","title":"Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation","created":"2024-10-08","cited_by_count":26},{"id":"2209.01857","title":"Statistical Comparisons of Classifiers by Generalized Stochastic Dominance","created":"2022-09-05","cited_by_count":20},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18},{"id":"2210.03165","title":"A Theory of Dynamic Benchmarks","created":"2022-10-06","cited_by_count":16},{"id":"2211.10797","title":"An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation","created":"2022-11-19","cited_by_count":14},{"id":"2306.12803","title":"Robust Statistical Comparison of Random Variables with Locally Varying Scale of Measurement","created":"2023-06-22","cited_by_count":13},{"id":"2403.04629","title":"Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration","created":"2024-03-07","cited_by_count":12},{"id":"2402.01632","title":"Time-Varying Gaussian Process Bandits with Unknown Prior","created":"2024-02-02","cited_by_count":11},{"id":"2406.03924","title":"Statistical Multicriteria Benchmarking via the GSD-Front","created":"2024-06-06","cited_by_count":11},{"id":"2110.12879","title":"Information efficient learning of complexly structured preferences: Elicitation procedures and their application to decision making under uncertainty","created":"2021-10-19","cited_by_count":10},{"id":"2302.08883","title":"Approximately Bayes-Optimal Pseudo Label Selection","created":"2023-02-17","cited_by_count":10},{"id":"2410.18653","title":"Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework","created":"2024-10-24","cited_by_count":9},{"id":"2402.16565","title":"Partial Rankings of Optimizers","created":"2024-02-26","cited_by_count":8},{"id":"2212.06832","title":"Multi-Target Decision Making under Conditions of Severe Uncertainty","created":"2022-12-13","cited_by_count":7},{"id":"2405.15294","title":"Semi-Supervised Learning guided by the Generalized Bayes Rule under Soft Revision","created":"2024-05-24","cited_by_count":6},{"id":"2502.07166","title":"Bayesian Optimization for Building Social-Influence-Free Consensus","created":"2025-02-11","cited_by_count":6},{"id":"2502.14581","title":"A Statistical Case Against Empirical Human-AI Alignment","created":"2025-02-20","cited_by_count":6},{"id":"2410.10452","title":"Principled Bayesian Optimisation in Collaboration with Human Experts","created":"2024-10-14","cited_by_count":5},{"id":"2312.12839","title":"Comparing Machine Learning Algorithms by Union-Free Generic Depth","created":"2023-12-20","cited_by_count":4},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3},{"id":"2501.10195","title":"Contributions to the Decision Theoretic Foundations of Machine Learning and Robust Statistics under Weakly Structured Information","created":"2025-01-17","cited_by_count":3}],"next_cursor":null}