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

arXiv: https://arxiv.org/abs/2310.05650 · HTML: https://mlsanity.com/paper/2310.05650/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 3 of its 62 references that are in the map.
- First posted on arXiv 9 Oct 2023.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 3 of 3)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization](https://mlsanity.com/paper/2305.11074/) (2023)

## Built on by (most cited first, 12 of 12)

- [DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection](https://mlsanity.com/paper/2402.10426/) (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)
- [NLP for Counterspeech against Hate: A Survey and How-To Guide](https://mlsanity.com/paper/2403.20103/) (2024)
- [A Multi-Aspect Framework for Counter Narrative Evaluation using Large Language Models](https://mlsanity.com/paper/2402.11676/) (2024)
- [MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge Distillation](https://mlsanity.com/paper/2403.14171/) (2024)
- [Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation](https://mlsanity.com/paper/2510.12316/) (2025)
- [Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation](https://mlsanity.com/paper/2605.22435/) (2026)
- [Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech](https://mlsanity.com/paper/2508.04638/) (2025)
- [Retrieval Augmented Enhanced Dual Co-Attention Framework for Target Aware Multimodal Bengali Hateful Meme Detection](https://mlsanity.com/paper/2602.19212/) (2026)
- [Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeech](https://mlsanity.com/paper/2607.26236/) (2026)
- [A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement](https://mlsanity.com/paper/2609.14178/) (2026)
- [Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech](https://mlsanity.com/paper/2609.16906/) (2026)

## Abstract (arXiv)

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.