Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation

TL;DR

This paper explores how Large Language Models can assist experts in generating counterspeech to combat hate speech and misinformation, emphasizing mixed strategies and expert revisions for improved effectiveness.

Contribution

It introduces a novel approach combining guidelines and documents for counterspeech generation in complex hate and misinformation contexts, supported by a new dataset.

Findings

LLMs produce adequate counterspeech in 40% of cases

Expert edits significantly improve naturalness and adherence to guidelines

Mixed strategy is most effective in crowdsourcing evaluations

Abstract

Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs) to assist expert counterspeech (CS) writing has gained interest, yet prior work has addressed these phenomena separately. We bridge this gap by studying CS generation in contexts where both hate and misinformation co-occur. We test three knowledge-driven generation strategies: first we prompt an LLM with fact-checkers' guidelines and fact-checking articles; secondly, with NGOs' guidelines and reports; thirdly, we create a mixed strategy that combines guidelines and documents from both. 23 experts revise the generated CS, which are assessed via human and automatic metrics. While LLMs produce adequate CS in 40% of cases, expert edits substantially improve naturalness, exhaustiveness, and adherence to guidelines. Based on the post-edited CS, the mixed strategy proves to be the most effective in crowdsourcing evaluation, pairing strong factual correction with stereotype mitigation and empathetic engagement. We release a dataset of hateful and misinformed claims with expert-verified CS and supporting knowledge.