{"total":17,"rows":[{"id":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26,"area":null},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2306.14115","title":"Towards Trustworthy Explanation: On Causal Rationalization","created":"2023-06-25","cited_by_count":19,"area":null},{"id":"2210.02659","title":"Explainable Abuse Detection as Intent Classification and Slot Filling","created":"2022-10-06","cited_by_count":11,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2406.03953","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2210.10689","title":"Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2307.01900","title":"Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers","created":"2023-07-04","cited_by_count":3,"area":null},{"id":"2402.02144","title":"Probing Critical Learning Dynamics of PLMs for Hate Speech Detection","created":"2024-02-03","cited_by_count":3,"area":null},{"id":"2305.18585","title":"Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models","created":"2023-05-29","cited_by_count":2,"area":null},{"id":"2602.18160","title":"Unifying Formal Explanations: A Complexity-Theoretic Perspective","created":"2026-02-20","cited_by_count":2,"area":null},{"id":"2410.13057","title":"ERAS: Evaluating the Robustness of Chinese NLP Models to Morphological Garden Path Errors","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2505.03746","title":"Promoting Security and Trust on Social Networks: Explainable Cyberbullying Detection Using Large Language Models in a Stream-Based Machine Learning Framework","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2509.09794","title":"Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2609.05385","title":"Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.18049","title":"Regional Explanations via Causal Sufficiency and Necessity","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.30151","title":"Does a model's stated reason for rejecting a candidate do any work?","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}