{"total":19,"rows":[{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2406.06046","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2303.09859","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","created":"2023-03-17","cited_by_count":39,"area":null},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2208.09770","title":"Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization","created":"2022-08-21","cited_by_count":29,"area":null},{"id":"2212.01853","title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","created":"2022-12-04","cited_by_count":24,"area":null},{"id":"2210.14867","title":"Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning","created":"2022-10-26","cited_by_count":16,"area":null},{"id":"2205.10981","title":"Improving Short Text Classification With Augmented Data Using GPT-3","created":"2022-05-23","cited_by_count":11,"area":null},{"id":"2306.06800","title":"AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2403.20329","title":"ReALM: Reference Resolution As Language Modeling","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2211.05044","title":"What is Wrong with Language Models that Can Not Tell a Story?","created":"2022-11-09","cited_by_count":4,"area":null},{"id":"2305.12567","title":"Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2310.07347","title":"Fast-ELECTRA for Efficient Pre-training","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2310.17591","title":"Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2312.08726","title":"Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2402.14890","title":"Vygotsky Distance: Measure for Benchmark Task Similarity","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2502.04797","title":"Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2401.13160","title":"SpacTor-T5: Pre-training T5 Models with Span Corruption and Replaced Token Detection","created":"2024-01-24","cited_by_count":0,"area":null}],"next_cursor":null}