{"total":76,"rows":[{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211,"area":null},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79,"area":null},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2305.07961","title":"Leveraging Large Language Models in Conversational Recommender Systems","created":"2023-05-13","cited_by_count":63,"area":null},{"id":"2101.00438","title":"Few-Shot Question Answering by Pretraining Span Selection","created":"2021-01-02","cited_by_count":62,"area":null},{"id":"2407.00128","title":"When Search Engine Services meet Large Language Models: Visions and Challenges","created":"2024-06-28","cited_by_count":59,"area":null},{"id":"2205.12679","title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning","created":"2022-05-25","cited_by_count":50,"area":null},{"id":"2211.12835","title":"Automatic Generation of Socratic Subquestions for Teaching Math Word Problems","created":"2022-11-23","cited_by_count":43,"area":null},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39,"area":null},{"id":"2112.09062","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","created":"2021-12-16","cited_by_count":31,"area":null},{"id":"2109.03438","title":"ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections","created":"2021-09-08","cited_by_count":30,"area":null},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","cited_by_count":30,"area":null},{"id":"2210.03992","title":"Generative Language Models for Paragraph-Level Question Generation","created":"2022-10-08","cited_by_count":28,"area":null},{"id":"2109.01951","title":"FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models","created":"2021-09-04","cited_by_count":26,"area":null},{"id":"2109.07954","title":"Improving Unsupervised Question Answering via Summarization-Informed Question Generation","created":"2021-09-16","cited_by_count":21,"area":null},{"id":"2108.13854","title":"Contrastive Domain Adaptation for Question Answering using Limited Text Corpora","created":"2021-08-31","cited_by_count":20,"area":null},{"id":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"area":null},{"id":"2302.01691","title":"LIQUID: A Framework for List Question Answering Dataset Generation","created":"2023-02-03","cited_by_count":19,"area":null},{"id":"2111.06467","title":"SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2205.12609","title":"Generating Information-Seeking Conversations from Unlabeled Documents","created":"2022-05-25","cited_by_count":17,"area":null},{"id":"2211.01482","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2206.02696","title":"Learning to Ask Like a Physician","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2305.17002","title":"An Empirical Comparison of LM-based Question and Answer Generation Methods","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2312.11036","title":"UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models","created":"2023-12-18","cited_by_count":14,"area":null},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2203.08926","title":"Synthetic Question Value Estimation for Domain Adaptation of Question Answering","created":"2022-03-16","cited_by_count":12,"area":null},{"id":"2205.12604","title":"Leveraging QA Datasets to Improve Generative Data Augmentation","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2310.05007","title":"MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering","created":"2023-10-08","cited_by_count":12,"area":null},{"id":"2401.17435","title":"Can LLMs Replace Economic Choice Prediction Labs? The Case of Language-based Persuasion Games","created":"2024-01-30","cited_by_count":12,"area":null},{"id":"2402.04335","title":"LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text","created":"2024-02-06","cited_by_count":12,"area":null},{"id":"2305.17416","title":"A Practical Toolkit for Multilingual Question and Answer Generation","created":"2023-05-27","cited_by_count":10,"area":null},{"id":"2204.11458","title":"ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference","created":"2022-04-25","cited_by_count":9,"area":null},{"id":"2210.04320","title":"QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation","created":"2022-10-09","cited_by_count":9,"area":null},{"id":"2310.07830","title":"Does Synthetic Data Make Large Language Models More Efficient?","created":"2023-10-11","cited_by_count":8,"area":null},{"id":"2408.02253","title":"Advancing Post-OCR Correction: A Comparative Study of Synthetic Data","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2408.13467","title":"LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs","created":"2024-08-24","cited_by_count":8,"area":null},{"id":"2109.07377","title":"Topic Transferable Table Question Answering","created":"2021-09-15","cited_by_count":7,"area":null},{"id":"2109.10346","title":"Relation-Guided Pre-Training for Open-Domain Question Answering","created":"2021-09-21","cited_by_count":7,"area":null},{"id":"2310.13505","title":"Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2110.08438","title":"Unsupervised Natural Language Inference Using PHL Triplet Generation","created":"2021-10-16","cited_by_count":6,"area":null},{"id":"2305.03088","title":"Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation","created":"2023-05-04","cited_by_count":6,"area":null},{"id":"2411.17993","title":"DRS: Deep Question Reformulation With Structured Output","created":"2024-11-27","cited_by_count":6,"area":null},{"id":"2211.14880","title":"Combining Data Generation and Active Learning for Low-Resource Question Answering","created":"2022-11-27","cited_by_count":5,"area":null},{"id":"2306.04101","title":"Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2411.01195","title":"Transfer Learning for Finetuning Large Language Models","created":"2024-11-02","cited_by_count":5,"area":null},{"id":"2210.13778","title":"IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension","created":"2022-10-25","cited_by_count":4,"area":null},{"id":"2312.17343","title":"AQUALLM: Audio Question Answering Data Generation Using Large Language Models","created":"2023-12-28","cited_by_count":4,"area":null},{"id":"2403.17582","title":"Towards a Zero-Data, Controllable, Adaptive Dialog System","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2409.01787","title":"LLM-GAN: Construct Generative Adversarial Network Through Large Language Models For Explainable Fake News Detection","created":"2024-09-03","cited_by_count":4,"area":null},{"id":"2605.15156","title":"MeMo: Memory as a Model","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2309.04739","title":"Data Augmentation for Conversational AI","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2310.15317","title":"Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2411.08553","title":"CorrSynth -- A Correlated Sampling Method for Diverse Dataset Generation from LLMs","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2204.02653","title":"Using Synthetic Data for Conversational Response Generation in Low-resource Settings","created":"2022-04-06","cited_by_count":2,"area":null},{"id":"2204.08009","title":"WikiOmnia: generative QA corpus on the whole Russian Wikipedia","created":"2022-04-17","cited_by_count":2,"area":null},{"id":"2211.08850","title":"Consecutive Question Generation via Dynamic Multitask Learning","created":"2022-11-16","cited_by_count":2,"area":null},{"id":"2406.17990","title":"Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2203.04464","title":"On the Evaluation of Answer-Agnostic Paragraph-level Multi-Question Generation","created":"2022-03-09","cited_by_count":1,"area":null},{"id":"2204.12263","title":"Science Checker: Extractive-Boolean Question Answering For Scientific Fact Checking","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2205.04050","title":"Few-shot Mining of Naturally Occurring Inputs and Outputs","created":"2022-05-09","cited_by_count":1,"area":null},{"id":"2301.08193","title":"JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its Applications","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2310.08072","title":"Training Generative Question-Answering on Synthetic Data Obtained from an Instruct-tuned Model","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2404.09206","title":"DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness","created":"2024-04-14","cited_by_count":1,"area":null},{"id":"2406.12381","title":"QOG:Question and Options Generation based on Language Model","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2502.20284","title":"Evaluating Human Trust in LLM-Based Planners: A Preliminary Study","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2509.08304","title":"Explainable Semantic Text Relations: A Question-Answering Framework for Comparing Document Content","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2604.17943","title":"A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2105.12833","title":"Simulated Data Generation Through Algorithmic Force Coefficient Estimation for AI-Based Robotic Projectile Launch Modeling","created":"2021-05-09","cited_by_count":0,"area":null},{"id":"2211.02971","title":"Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference","created":"2022-11-05","cited_by_count":0,"area":null},{"id":"2212.10558","title":"On-the-fly Denoising for Data Augmentation in Natural Language Understanding","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2303.09056","title":"Generating synthetic multi-dimensional molecular-mediator time series data for artificial intelligence-based disease trajectory forecasting and drug development digital twins: Considerations","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2409.13749","title":"KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2409.15188","title":"PALLM: Evaluating and Enhancing PALLiative Care Conversations with Large Language Models","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2606.27047","title":"NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":null}