# Evaluating GPT-3 Generated Explanations for Hateful Content Moderation

arXiv: https://arxiv.org/abs/2305.17680 · HTML: https://mlsanity.com/paper/2305.17680/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 57 references that are in the map.
- First posted on arXiv 28 May 2023.

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [Reducing Gender Bias in Abusive Language Detection](https://mlsanity.com/paper/1808.07231/) (2018)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Deceiving Google's Perspective API Built for Detecting Toxic Comments](https://mlsanity.com/paper/1702.08138/) (2017)
- [Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text](https://mlsanity.com/paper/2107.01294/) (2021)
- [Generating Counter Narratives against Online Hate Speech: Data and Strategies](https://mlsanity.com/paper/2004.04216/) (2020)
- [Detecting Hate Speech with GPT-3](https://mlsanity.com/paper/2103.12407/) (2021)
- [Toxicity Detection with Generative Prompt-based Inference](https://mlsanity.com/paper/2205.12390/) (2022)
- [DeepHate: Hate Speech Detection via Multi-Faceted Text Representations](https://mlsanity.com/paper/2103.11799/) (2021)
- [AngryBERT: Joint Learning Target and Emotion for Hate Speech Detection](https://mlsanity.com/paper/2103.11800/) (2021)
- [Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection](https://mlsanity.com/paper/2303.02513/) (2023)
- [Predicting Hate Intensity of Twitter Conversation Threads](https://mlsanity.com/paper/2206.08406/) (2022)

## Built on by (most cited first, 30 of 46)

- [Composite Backdoor Attacks Against Large Language Models](https://mlsanity.com/paper/2310.07676/) (2023)
- [Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom](https://mlsanity.com/paper/2405.03371/) (2024)
- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)
- [Unveiling Gender Bias in Terms of Profession Across LLMs: Analyzing and Addressing Sociological Implications](https://mlsanity.com/paper/2307.09162/) (2023)
- [Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models](https://mlsanity.com/paper/2401.16727/) (2024)
- [What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection](https://mlsanity.com/paper/2402.00371/) (2024)
- [DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures](https://mlsanity.com/paper/2403.14651/) (2024)
- [MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention](https://mlsanity.com/paper/2406.05344/) (2024)
- [User Modeling in the Era of Large Language Models: Current Research and Future Directions](https://mlsanity.com/paper/2312.11518/) (2023)
- [ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?](https://mlsanity.com/paper/2403.17368/) (2024)
- [Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement](https://mlsanity.com/paper/2502.06207/) (2025)
- [Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions](https://mlsanity.com/paper/2502.11073/) (2025)
- [Legilimens: Practical and Unified Content Moderation for Large Language Model Services](https://mlsanity.com/paper/2408.15488/) (2024)
- [Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD](https://mlsanity.com/paper/2508.17450/) (2025)
- [SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore](https://mlsanity.com/paper/2405.01842/) (2024)
- [BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla](https://mlsanity.com/paper/2410.13281/) (2024)
- [MemeIntel: Explainable Detection of Propagandistic and Hateful Memes](https://mlsanity.com/paper/2502.16612/) (2025)
- [Cross-Modal Transfer from Memes to Videos: Addressing Data Scarcity in Hateful Video Detection](https://mlsanity.com/paper/2501.15438/) (2025)
- [Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM](https://mlsanity.com/paper/2508.05775/) (2025)
- [HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models](https://mlsanity.com/paper/2310.13985/) (2023)
- [PropXplain: Can LLMs Enable Explainable Propaganda Detection?](https://mlsanity.com/paper/2502.16550/) (2025)
- [Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster](https://mlsanity.com/paper/2406.04106/) (2024)
- [Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions](https://mlsanity.com/paper/2507.22617/) (2025)
- [HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models](https://mlsanity.com/paper/2403.11456/) (2024)
- [LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation](https://mlsanity.com/paper/2503.07237/) (2025)
- [OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA](https://mlsanity.com/paper/2510.06371/) (2025)
- [When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output](https://mlsanity.com/paper/2503.24191/) (2025)
- [HateClipSeg: A Segment-Level Annotated Dataset for Fine-Grained Hate Video Detection](https://mlsanity.com/paper/2508.01712/) (2025)
- [Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation](https://mlsanity.com/paper/2604.05083/) (2026)
- [Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges](https://mlsanity.com/paper/2401.09244/) (2024)

## Abstract (arXiv)

Recent research has focused on using large language models (LLMs) to generate explanations for hate speech through fine-tuning or prompting. Despite the growing interest in this area, these generated explanations' effectiveness and potential limitations remain poorly understood. A key concern is that these explanations, generated by LLMs, may lead to erroneous judgments about the nature of flagged content by both users and content moderators. For instance, an LLM-generated explanation might inaccurately convince a content moderator that a benign piece of content is hateful. In light of this, we propose an analytical framework for examining hate speech explanations and conducted an extensive survey on evaluating such explanations. Specifically, we prompted GPT-3 to generate explanations for both hateful and non-hateful content, and a survey was conducted with 2,400 unique respondents to evaluate the generated explanations. Our findings reveal that (1) human evaluators rated the GPT-generated explanations as high quality in terms of linguistic fluency, informativeness, persuasiveness, and logical soundness, (2) the persuasive nature of these explanations, however, varied depending on the prompting strategy employed, and (3) this persuasiveness may result in incorrect judgments about the hatefulness of the content. Our study underscores the need for caution in applying LLM-generated explanations for content moderation. Code and results are available at https://github.com/Social-AI-Studio/GPT3-HateEval.