{"total":19,"rows":[{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39,"area":null},{"id":"2501.18845","title":"Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunities","created":"2025-01-31","cited_by_count":22,"area":null},{"id":"2109.05897","title":"Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework","created":"2021-09-13","cited_by_count":21,"area":null},{"id":"2210.14494","title":"CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Course","created":"2022-10-26","cited_by_count":11,"area":null},{"id":"2304.09660","title":"MPMQA: Multimodal Question Answering on Product Manuals","created":"2023-04-19","cited_by_count":10,"area":null},{"id":"2309.12426","title":"Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges","created":"2023-09-21","cited_by_count":9,"area":null},{"id":"2106.04134","title":"Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2505.14212","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2101.03999","title":"A Neural Question Answering System for Basic Questions about Subroutines","created":"2021-01-11","cited_by_count":5,"area":null},{"id":"2406.00975","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2408.03630","title":"PAGED: A Benchmark for Procedural Graphs Extraction from Documents","created":"2024-08-07","cited_by_count":4,"area":null},{"id":"2302.01806","title":"Mitigating Data Scarcity for Large Language Models","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2403.09131","title":"ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses","created":"2024-03-14","cited_by_count":2,"area":null},{"id":"2409.18446","title":"Exploring Language Model Generalization in Low-Resource Extractive QA","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2509.21732","title":"How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2401.07977","title":"Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2105.03229","title":"VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension","created":"2021-05-07","cited_by_count":0,"area":null},{"id":"2306.06190","title":"$FastDoc$: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy","created":"2023-06-09","cited_by_count":0,"area":null}],"next_cursor":null}