{"list":"other","total":60,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"1907.04135","title":"The What-If Tool: Interactive Probing of Machine Learning Models","created":"2019-07-09","cited_by_count":207},{"id":"2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","created":"2024-02-26","cited_by_count":205},{"id":"2111.05328","title":"Data Augmentation Can Improve Robustness","created":"2021-11-09","cited_by_count":194},{"id":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192},{"id":"2004.12239","title":"MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification","created":"2020-04-25","cited_by_count":187},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"id":"2008.05122","title":"The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models","created":"2020-08-12","cited_by_count":125},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111},{"id":"2309.09128","title":"ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing","created":"2023-09-17","cited_by_count":88},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83},{"id":"1904.02323","title":"Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations","created":"2019-04-04","cited_by_count":72},{"id":"1804.09299","title":"Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models","created":"2018-04-25","cited_by_count":69},{"id":"2304.09337","title":"Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models","created":"2023-04-18","cited_by_count":67},{"id":"1908.00176","title":"FairSight: Visual Analytics for Fairness in Decision Making","created":"2019-08-01","cited_by_count":59},{"id":"2307.09036","title":"PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation","created":"2023-07-18","cited_by_count":58},{"id":"2004.15004","title":"CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization","created":"2020-04-30","cited_by_count":57},{"id":"1910.04176","title":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","created":"2019-10-09","cited_by_count":45},{"id":"1611.05469","title":"Embedding Projector: Interactive Visualization and Interpretation of Embeddings","created":"2016-11-16","cited_by_count":44},{"id":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","cited_by_count":43},{"id":"2010.01794","title":"GenAug: Data Augmentation for Finetuning Text Generators","created":"2020-10-05","cited_by_count":41},{"id":"2010.08670","title":"CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding","created":"2020-10-16","cited_by_count":41},{"id":"2211.02843","title":"Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift","created":"2022-11-05","cited_by_count":38},{"id":"2308.05184","title":"PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions","created":"2023-08-09","cited_by_count":34},{"id":"2007.13632","title":"Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing","created":"2020-07-27","cited_by_count":32},{"id":"2402.10524","title":"LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models","created":"2024-02-16","cited_by_count":29},{"id":"2402.15350","title":"Farsight: Fostering Responsible AI Awareness During AI Application Prototyping","created":"2024-02-23","cited_by_count":28},{"id":"2401.13726","title":"Supporting Sensemaking of Large Language Model Outputs at Scale","created":"2024-01-24","cited_by_count":27},{"id":"2303.01580","title":"Mixture of Soft Prompts for Controllable Data Generation","created":"2023-03-02","cited_by_count":23},{"id":"2003.08529","title":"Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections","created":"2020-03-19","cited_by_count":22},{"id":"2310.09985","title":"Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets","created":"2023-10-15","cited_by_count":22},{"id":"2008.07466","title":"Narrative Interpolation for Generating and Understanding Stories","created":"2020-08-17","cited_by_count":19},{"id":"2010.01475","title":"Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space","created":"2020-10-04","cited_by_count":19},{"id":"2402.08855","title":"GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency","created":"2024-02-13","cited_by_count":18},{"id":"2312.11681","title":"Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows","created":"2023-12-18","cited_by_count":17},{"id":"1704.07434","title":"Paying Attention to Descriptions Generated by Image Captioning Models","created":"2017-04-24","cited_by_count":12},{"id":"2209.02529","title":"Erato: Cooperative Data Story Editing via Fact Interpolation","created":"2022-09-06","cited_by_count":11},{"id":"2403.09615","title":"PrompTHis: Visualizing the Process and Influence of Prompt Editing during Text-to-Image Creation","created":"2024-03-14","cited_by_count":11},{"id":"2406.11654","title":"Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming","created":"2024-06-17","cited_by_count":10},{"id":"2301.04528","title":"The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference","created":"2023-01-11","cited_by_count":9},{"id":"2307.07099","title":"Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation","created":"2023-07-14","cited_by_count":9},{"id":"2309.07110","title":"Data Augmentation via Subgroup Mixup for Improving Fairness","created":"2023-09-13","cited_by_count":8},{"id":"2402.14880","title":"Automatic Histograms: Leveraging Language Models for Text Dataset Exploration","created":"2024-02-21","cited_by_count":8},{"id":"2407.07786","title":"The Human Factor in AI Red Teaming: Perspectives from Social and Collaborative Computing","created":"2024-07-10","cited_by_count":8},{"id":"2212.08167","title":"Evaluation of Synthetic Datasets for Conversational Recommender Systems","created":"2022-12-12","cited_by_count":6},{"id":"2408.14504","title":"Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes","created":"2024-08-24","cited_by_count":5},{"id":"2301.04518","title":"Large Scale Qualitative Evaluation of Generative Image Model Outputs","created":"2023-01-11","cited_by_count":4},{"id":"1705.05283","title":"Visualizing Dimensionality Reduction Artifacts: An Evaluation","created":"2017-05-15","cited_by_count":3}],"next_cursor":null}