{"total":19,"rows":[{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2109.09483","title":"ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI","created":"2021-09-20","cited_by_count":46,"area":null},{"id":"2404.17874","title":"From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets","created":"2024-04-27","cited_by_count":25,"area":null},{"id":"2205.03302","title":"Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection","created":"2022-05-06","cited_by_count":18,"area":null},{"id":"2204.02261","title":"Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors","created":"2022-04-05","cited_by_count":14,"area":null},{"id":"2411.15462","title":"HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter","created":"2024-11-23","cited_by_count":13,"area":null},{"id":"2403.19260","title":"NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2207.10032","title":"Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2205.01374","title":"Hidden behind the obvious: misleading keywords and implicitly abusive language on social media","created":"2022-05-03","cited_by_count":6,"area":null},{"id":"2201.06384","title":"Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2410.15314","title":"KTCR: Improving Implicit Hate Detection with Knowledge Transfer driven Concept Refinement","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2312.09043","title":"Topic Bias in Emotion Classification","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2503.05357","title":"Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2504.13085","title":"Tackling Social Bias against the Poor: A Dataset and Taxonomy on Aporophobia","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2606.18852","title":"Aligning Implied Statements for Implicit Hate Speech Generalizability with Context-Bounded Semi-hard Negative Mining","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.23512","title":"The Cross-Domain Generalization Cost of Offensive Language Detection","created":"2026-07-26","cited_by_count":0,"area":null}],"next_cursor":null}