Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech

2026-09-15

AI Summary

本文提出了一种新的范围条件生成框架，通过将结构化的刻板印象特征整合到大型语言模型提示中，有效生成多语言反言论，以应对在线仇恨言论。

Abstract

Counterspeech (CS) - direct responses that counter online Hate Speech (HS) using reasoning and alternative viewpoints - has emerged as an alternative to content removal. Current automatic CS generation methods, however, frequently produce generic, ineffective replies that fail to target the implicit stereotypes behind HS. To bridge this gap, we propose a novel scope-conditioned generation framework that explicitly integrates structured stereotype characteristics into Large Language Models prompts. We validate our approach on a novel, human-curated dataset annotated in English, Italian, and Spanish. Extensive evaluations show that stereotype-conditioned prompting substantially outperforms generic baselines across all three languages, obtaining significant gains in factuality, specificity, cogency, and effectiveness for both explicit and implicit implied stereotypes.

Problem

• Counterspeech
• Hate Speech
• Stereotypes

Innovation

• scope-conditioned generation
• stereotype characteristics
• large language models
• counterspeech effectiveness