# Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering arXiv: https://arxiv.org/abs/2410.03466 ยท HTML: https://mlsanity.com/paper/2410.03466/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security. - Builds on 19 of its 41 references that are in the map. - First posted on arXiv 4 Oct 2024. ## Placed in - LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/) ## Builds on (most cited first, 19 of 19) - [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022) - [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021) - [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018) - [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://mlsanity.com/paper/1909.04251/) (2019) - [Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech](https://mlsanity.com/paper/2107.08720/) (2021) - [Generating Counter Narratives against Online Hate Speech: Data and Strategies](https://mlsanity.com/paper/2004.04216/) (2020) - [Argument Generation with Retrieval, Planning, and Realization](https://mlsanity.com/paper/1906.03717/) (2019) - [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) - [Neural Argument Generation Augmented with Externally Retrieved Evidence](https://mlsanity.com/paper/1805.10254/) (2018) - [Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study](https://mlsanity.com/paper/2204.01440/) (2022) - [Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language](https://mlsanity.com/paper/2311.00161/) (2023) - [Argument Undermining: Counter-Argument Generation by Attacking Weak Premises](https://mlsanity.com/paper/2105.11752/) (2021) - [NLP for Counterspeech against Hate: A Survey and How-To Guide](https://mlsanity.com/paper/2403.20103/) (2024) - [Detecting Attackable Sentences in Arguments](https://mlsanity.com/paper/2010.02660/) (2020) - [Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation](https://mlsanity.com/paper/2312.13608/) (2023) - [Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization](https://mlsanity.com/paper/2309.02311/) (2023) - [Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation](https://mlsanity.com/paper/2403.09159/) (2024) - [Which Argumentative Aspects of Hate Speech in Social Media can be reliably identified?](https://mlsanity.com/paper/2306.02978/) (2023) ## Built on by (most cited first, 11 of 11) - [A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection](https://mlsanity.com/paper/2411.12946/) (2024) - [Debunking with Dialogue? Exploring AI-Generated Counterspeech to Challenge Conspiracy Theories](https://mlsanity.com/paper/2504.16604/) (2025) - [Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation](https://mlsanity.com/paper/2510.12316/) (2025) - [Left, Right, or Center? Evaluating LLM Framing in News Classification and Generation](https://mlsanity.com/paper/2601.05835/) (2026) - [When Hate Meets Facts: LLMs-in-the-Loop for Check-worthiness Detection in Hate Speech](https://mlsanity.com/paper/2603.25269/) (2026) - [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) - [PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressions](https://mlsanity.com/paper/2602.17467/) (2026) - [Leveraging Argument Structure to Predict Content Hatefulness](https://mlsanity.com/paper/2605.02457/) (2026) - [CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges](https://mlsanity.com/paper/2606.20369/) (2026) - [Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech](https://mlsanity.com/paper/2609.16906/) (2026) ## Abstract (arXiv) The potential effectiveness of counterspeech as a hate speech mitigation strategy is attracting increasing interest in the NLG research community, particularly towards the task of automatically producing it. However, automatically generated responses often lack the argumentative richness which characterises expert-produced counterspeech. In this work, we focus on two aspects of counterspeech generation to produce more cogent responses. First, by investigating the tension between helpfulness and harmlessness of LLMs, we test whether the presence of safety guardrails hinders the quality of the generations. Secondly, we assess whether attacking a specific component of the hate speech results in a more effective argumentative strategy to fight online hate. By conducting an extensive human and automatic evaluation, we show how the presence of safety guardrails can be detrimental also to a task that inherently aims at fostering positive social interactions. Moreover, our results show that attacking a specific component of the hate speech, and in particular its implicit negative stereotype and its hateful parts, leads to higher-quality generations.