# Debunking with Dialogue? Exploring AI-Generated Counterspeech to Challenge Conspiracy Theories

arXiv: https://arxiv.org/abs/2504.16604 · HTML: https://mlsanity.com/paper/2504.16604/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 72 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://mlsanity.com/paper/1909.04251/) (2019)
- [CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech](https://mlsanity.com/paper/1910.03270/) (2019)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech](https://mlsanity.com/paper/2106.11783/) (2021)
- [Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering](https://mlsanity.com/paper/2211.03433/) (2022)
- [Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study](https://mlsanity.com/paper/2204.01440/) (2022)
- [Large Language Models Show Human-like Social Desirability Biases in Survey Responses](https://mlsanity.com/paper/2405.06058/) (2024)
- [Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language](https://mlsanity.com/paper/2311.00161/) (2023)
- [NLP for Counterspeech against Hate: A Survey and How-To Guide](https://mlsanity.com/paper/2403.20103/) (2024)
- [Understanding Counterspeech for Online Harm Mitigation](https://mlsanity.com/paper/2307.04761/) (2023)
- [On Zero-Shot Counterspeech Generation by LLMs](https://mlsanity.com/paper/2403.14938/) (2024)
- [Counterspeakers' Perspectives: Unveiling Barriers and AI Needs in the Fight against Online Hate](https://mlsanity.com/paper/2403.00179/) (2024)
- [Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluation](https://mlsanity.com/paper/2412.07338/) (2024)
- [Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering](https://mlsanity.com/paper/2410.03466/) (2024)
- [The Impact of Example Selection in Few-Shot Prompting on Automated Essay Scoring Using GPT Models](https://mlsanity.com/paper/2411.18924/) (2024)
- [Belief in the Machine: Investigating Epistemological Blind Spots of Language Models](https://mlsanity.com/paper/2410.21195/) (2024)
- [Detection of Conspiracy Theories Beyond Keyword Bias in German-Language Telegram Using Large Language Models](https://mlsanity.com/paper/2404.17985/) (2024)
- [A feast for trolls -- Engagement analysis of counternarratives against online toxicity](https://mlsanity.com/paper/2111.07188/) (2021)
- [A Hate Speech Moderated Chat Application: Use Case for GDPR and DSA Compliance](https://mlsanity.com/paper/2410.07713/) (2024)

## Built on by (most cited first, 2 of 2)

- [ConspirED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety](https://mlsanity.com/paper/2508.20468/) (2025)
- [Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation](https://mlsanity.com/paper/2605.22435/) (2026)

## Abstract (arXiv)

Counterspeech is a key strategy against harmful online content, but scaling expert-driven efforts is challenging. Large Language Models (LLMs) present a potential solution, though their use in countering conspiracy theories is under-researched. Unlike for hate speech, no datasets exist that pair conspiracy theory comments with expert-crafted counterspeech. We address this gap by evaluating the ability of GPT-4o, Llama 3, and Mistral to effectively apply counterspeech strategies derived from psychological research provided through structured prompts. Our results show that the models often generate generic, repetitive, or superficial results. Additionally, they over-acknowledge fear and frequently hallucinate facts, sources, or figures, making their prompt-based use in practical applications problematic.