{"total":24,"rows":[{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2304.09991","title":"Supporting Human-AI Collaboration in Auditing LLMs with LLMs","created":"2023-04-19","cited_by_count":46,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"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":"2110.07596","title":"Retrieval-guided Counterfactual Generation for QA","created":"2021-10-14","cited_by_count":29,"area":null},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16,"area":null},{"id":"2210.03165","title":"A Theory of Dynamic Benchmarks","created":"2022-10-06","cited_by_count":16,"area":null},{"id":"2111.08181","title":"Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair","created":"2021-11-16","cited_by_count":12,"area":null},{"id":"2107.13935","title":"Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition","created":"2021-07-29","cited_by_count":11,"area":null},{"id":"2203.06342","title":"What Makes Reading Comprehension Questions Difficult?","created":"2022-03-12","cited_by_count":11,"area":null},{"id":"2212.00921","title":"AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization","created":"2022-12-02","cited_by_count":10,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2206.14729","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks","created":"2022-06-29","cited_by_count":8,"area":null},{"id":"2406.16342","title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2111.10497","title":"Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution","created":"2021-11-20","cited_by_count":1,"area":null},{"id":"2206.04039","title":"Resolving the Human Subjects Status of Machine Learning's Crowdworkers","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2210.13678","title":"Bridging the Training-Inference Gap for Dense Phrase Retrieval","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2206.14272","title":"Collecting high-quality adversarial data for machine reading comprehension tasks with humans and models in the loop","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2309.03238","title":"Implicit Design Choices and Their Impact on Emotion Recognition Model Development and Evaluation","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2601.11581","title":"Enhancing the QA Model through a Multi-domain Debiasing Framework","created":"2026-01-01","cited_by_count":0,"area":null}],"next_cursor":null}