ReZG: Retrieval-Augmented Zero-Shot Counter Narrative Generation for Hate Speech

TL;DR

ReZG introduces a retrieval-augmented zero-shot method for generating highly specific counter narratives to combat hate speech, overcoming data annotation limitations and generalizing to unseen targets effectively.

Contribution

It proposes a multi-dimensional retrieval and energy-based constrained decoding approach enabling zero-shot counter narrative generation for unseen hate speech targets.

Findings

ReZG outperforms baselines with 2.0%+ relevance improvement.

ReZG achieves 4.5%+ higher countering success rate.

The method demonstrates strong generalization to unseen hate speech targets.

Abstract

The proliferation of hate speech (HS) on social media poses a serious threat to societal security. Automatic counter narrative (CN) generation, as an active strategy for HS intervention, has garnered increasing attention in recent years. Existing methods for automatically generating CNs mainly rely on re-training or fine-tuning pre-trained language models (PLMs) on human-curated CN corpora. Unfortunately, the annotation speed of CN corpora cannot keep up with the growth of HS targets, while generating specific and effective CNs for unseen targets remains a significant challenge for the model. To tackle this issue, we propose Retrieval-Augmented Zero-shot Generation (ReZG) to generate CNs with high-specificity for unseen targets. Specifically, we propose a multi-dimensional hierarchical retrieval method that integrates stance, semantics, and fitness, extending the retrieval metric from single dimension to multiple dimensions suitable for the knowledge that refutes HS. Then, we implement an energy-based constrained decoding mechanism that enables PLMs to use differentiable knowledge preservation, countering, and fluency constraint functions instead of in-target CNs as control signals for generation, thereby achieving zero-shot CN generation. With the above techniques, ReZG can integrate external knowledge flexibly and improve the specificity of CNs. Experimental results show that ReZG exhibits stronger generalization capabilities and outperforms strong baselines with significant improvements of 2.0%+ in the relevance and 4.5%+ in the countering success rate metrics.