{"total":33,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2307.00524","title":"Large Language Models Enable Few-Shot Clustering","created":"2023-07-02","cited_by_count":72,"area":null},{"id":"2206.08931","title":"CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation","created":"2022-06-09","cited_by_count":59,"area":null},{"id":"2212.10276","title":"Identifying and Manipulating the Personality Traits of Language Models","created":"2022-12-20","cited_by_count":40,"area":null},{"id":"2207.02942","title":"Towards Transparency in Dermatology Image Datasets with Skin Tone Annotations by Experts, Crowds, and an Algorithm","created":"2022-07-06","cited_by_count":35,"area":null},{"id":"2112.11941","title":"CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models","created":"2021-12-22","cited_by_count":34,"area":null},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2104.07179","title":"Does Putting a Linguist in the Loop Improve NLU Data Collection?","created":"2021-04-15","cited_by_count":29,"area":null},{"id":"2109.14646","title":"FathomNet: A global image database for enabling artificial intelligence in the ocean","created":"2021-09-29","cited_by_count":25,"area":null},{"id":"2203.16000","title":"StyleFool: Fooling Video Classification Systems via Style Transfer","created":"2022-03-30","cited_by_count":20,"area":null},{"id":"2311.02802","title":"Incorporating Worker Perspectives into MTurk Annotation Practices for NLP","created":"2023-11-06","cited_by_count":18,"area":null},{"id":"2205.11963","title":"The Data-Production Dispositif","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2101.00379","title":"Investigating Memorization of Conspiracy Theories in Text Generation","created":"2021-01-02","cited_by_count":15,"area":null},{"id":"2111.05241","title":"A Survey of NLP-Related Crowdsourcing HITs: what works and what does not","created":"2021-11-09","cited_by_count":15,"area":null},{"id":"2207.11569","title":"Robots Enact Malignant Stereotypes","created":"2022-07-23","cited_by_count":14,"area":null},{"id":"2402.13764","title":"CriticEval: Evaluating Large Language Model as Critic","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2105.12762","title":"Quantifying and Avoiding Unfair Qualification Labour in Crowdsourcing","created":"2021-05-26","cited_by_count":11,"area":null},{"id":"2109.08131","title":"Studying Up Machine Learning Data: Why Talk About Bias When We Mean Power?","created":"2021-09-16","cited_by_count":11,"area":null},{"id":"2502.00198","title":"Fairshare Data Pricing via Data Valuation for Large Language Models","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2407.12015","title":"The Great AI Witch Hunt: Reviewers Perception and (Mis)Conception of Generative AI in Research Writing","created":"2024-06-27","cited_by_count":6,"area":null},{"id":"2102.00423","title":"Characterizing Student Engagement Moods for Dropout Prediction in Question Pool Websites","created":"2021-01-31","cited_by_count":4,"area":null},{"id":"2408.01458","title":"Surveys Considered Harmful? Reflecting on the Use of Surveys in AI Research, Development, and Governance","created":"2024-07-26","cited_by_count":4,"area":null},{"id":"2410.13868","title":"Stars, Stripes, and Silicon: Unravelling the ChatGPT's All-American, Monochrome, Cis-centric Bias","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2306.01800","title":"The ethical ambiguity of AI data enrichment: Measuring gaps in research ethics norms and practices","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2311.03567","title":"Inclusive Portraits: Race-Aware Human-in-the-Loop Technology","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2402.08242","title":"Towards Equitable Agile Research and Development of AI and Robotics","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2407.08514","title":"Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systems","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2403.17238","title":"Temporal and Semantic Evaluation Metrics for Foundation Models in Post-Hoc Analysis of Robotic Sub-tasks","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2207.02960","title":"The \"Collections as ML Data\" Checklist for Machine Learning & Cultural Heritage","created":"2022-07-06","cited_by_count":0,"area":null},{"id":"2408.07838","title":"A Culturally-Aware Tool for Crowdworkers: Leveraging Chronemics to Support Diverse Work Styles","created":"2024-07-31","cited_by_count":0,"area":null},{"id":"2501.06981","title":"Data Enrichment Work and AI Labor in Latin America and the Caribbean","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2503.21000","title":"Improving User Behavior Prediction: Leveraging Annotator Metadata in Supervised Machine Learning Models","created":"2025-03-26","cited_by_count":0,"area":null}],"next_cursor":null}