# Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning

arXiv: https://arxiv.org/abs/2505.11958 · HTML: https://mlsanity.com/paper/2505.11958/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 17 May 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://mlsanity.com/paper/1909.04251/) (2019)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech](https://mlsanity.com/paper/1910.03270/) (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)
- [Thou shalt not hate: Countering Online Hate Speech](https://mlsanity.com/paper/1808.04409/) (2018)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering](https://mlsanity.com/paper/2211.03433/) (2022)
- [CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech](https://mlsanity.com/paper/2205.04304/) (2022)
- [AngryBERT: Joint Learning Target and Emotion for Hate Speech Detection](https://mlsanity.com/paper/2103.11800/) (2021)
- [Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization](https://mlsanity.com/paper/2206.04007/) (2022)
- [Understanding Counterspeech for Online Harm Mitigation](https://mlsanity.com/paper/2307.04761/) (2023)
- [Hate is the New Infodemic: A Topic-aware Modeling of Hate Speech Diffusion on Twitter](https://mlsanity.com/paper/2010.04377/) (2020)
- [Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation](https://mlsanity.com/paper/2305.13776/) (2023)
- [Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF](https://mlsanity.com/paper/2403.10088/) (2024)
- [Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech](https://mlsanity.com/paper/2406.03953/) (2024)
- [CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs](https://mlsanity.com/paper/2501.17581/) (2025)
- [Independent fact-checking organizations exhibit a departure from political neutrality](https://mlsanity.com/paper/2407.19498/) (2024)
- [Overview of the HASOC Subtrack at FIRE 2023: Identification of Tokens Contributing to Explicit Hate in English by Span Detection](https://mlsanity.com/paper/2311.09834/) (2023)

## Built on by (most cited first, 2 of 2)

- [Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeech](https://mlsanity.com/paper/2607.26236/) (2026)
- [Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation](https://mlsanity.com/paper/2608.23152/) (2026)

## Abstract (arXiv)

Counterspeech has proven to be a powerful tool to combat hate speech online. Previous studies have focused on generating counterspeech conditioned only on specific intents (single attributed). However, a holistic approach considering multiple attributes simultaneously can yield more nuanced and effective responses. Here, we introduce HiPPrO, Hierarchical Prefix learning with Preference Optimization, a novel two-stage framework that utilizes the effectiveness of attribute-specific prefix embedding spaces hierarchically optimized during the counterspeech generation process in the first phase. Thereafter, we incorporate both reference and reward-free preference optimization to generate more constructive counterspeech. Furthermore, we extend IntentCONANv2 by annotating all 13,973 counterspeech instances with emotion labels by five annotators. HiPPrO leverages hierarchical prefix optimization to integrate these dual attributes effectively. An extensive evaluation demonstrates that HiPPrO achieves a ~38 % improvement in intent conformity and a ~3 %, ~2 %, ~3 % improvement in Rouge-1, Rouge-2, and Rouge-L, respectively, compared to several baseline models. Human evaluations further substantiate the superiority of our approach, highlighting the enhanced relevance and appropriateness of the generated counterspeech. This work underscores the potential of multi-attribute conditioning in advancing the efficacy of counterspeech generation systems. Our code is available on Github and dataset is open-sourced on Hugging-face.