mlsanityData to 7 Oct 2026

Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech

arXiv 2209.04889 ↗First posted 11 Sep 2022cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

Recent studies have exploited advanced generative language models to generate Natural Language Explanations (NLE) for why a certain text could be hateful. We propose the Chain of Explanation (CoE) Prompting method, using the heuristic words and target group, to generate high-quality NLE for implicit hate speech. We improved the BLUE score from 44.0 to 62.3 for NLE generation by providing accurate target information. We then evaluate the quality of generated NLE using various automatic metrics and human annotations of informativeness and clarity scores.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 19 of its 29 references that are in the map. First posted on arXiv 11 Sep 2022.

Builds on

19 of 29 references.

References · 19

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  8. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  9. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  10. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  11. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  12. 2017Learning Explanatory Rules from Noisy Datacited by 210
7 more
  1. 2021OpenPrompt: An Open-source Framework for Prompt-learningcited by 148
  2. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  3. 2020NUBIA: NeUral Based Interchangeability Assessor for Text Generationcited by 34
  4. 2021A Study of Automatic Metrics for the Evaluation of Natural Language Explanationscited by 34
  5. 2016Kek, Cucks, and God Emperor Trump: A Measurement Study of 4chan's Politically Incorrect Forum and Its Effects on the Webcited by 15
  6. 2021Investigating Memorization of Conspiracy Theories in Text Generationcited by 15
  7. 2021Do explanations increase the effectiveness of AI-crowd generated fake news warnings?cited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 9; 2025: 5; 2026: 5.

25 papers.

Sort:

By area:

  1. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  2. 2023Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speechcited by 165
  3. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  4. 2024Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Eracited by 45
  5. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  6. 2023Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AIcited by 32
  7. 2024AI for social science and social science of AI: A Surveycited by 29
  8. 2024An Investigation of Large Language Models for Real-World Hate Speech Detectioncited by 20
  9. 2023Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Modelscited by 17
  10. 2024ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?cited by 17
  11. 2024Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Modelscited by 13
  12. 2024Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speechcited by 11
13 more
  1. 2025MemeIntel: Explainable Detection of Propagandistic and Hateful Memescited by 8
  2. 2024Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Modelscited by 7
  3. 2023Self-Explanation Prompting Improves Dialogue Understanding in Large Language Modelscited by 5
  4. 2025OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QAcited by 5
  5. 2024Graph-Guided Textual Explanation Generation Frameworkcited by 3
  6. 2026Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluationcited by 3
  7. 2025Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classificationcited by 2
  8. 2025Chinese Cyberbullying Detection: Dataset, Method, and Validationcited by 1
  9. 2026Vulnerability of LLMs' Stated Beliefs? LLMs Belief Resistance Check Through Strategic Persuasive Conversation Interventionscited by 1
  10. 2026Chain-of-Experience for Continual LLM Improvementcited by 1
  11. 2025From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discoursecited by 0
  12. 2026KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learningcited by 0
  13. 2026Explain the Flag: Contextualizing Hate Speech Beyond Censorshipcited by 0