Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation

• URL: http://arxiv.org/abs/2510.12316v1
• Date: Tue, 14 Oct 2025 09:20:01 GMT
• Title: Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation
• Authors: Greta Damo, Elena Cabrio, Serena Villata,
• Abstract summary: We introduce a novel framework to model counter-speech generation as knowledge-wise text generation process.<n>Our framework integrates advanced Retrieval-Augmented Generation (RAG) pipelines to ensure the generation of trustworthy counter-speech for 8 main target groups.<n>We use the MultiTarget-CONAN dataset to empirically assess the quality of the generated counter-speech, both through standard metrics and a human evaluation.
• Score: 10.488285141408253
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Counter-speech generation is at the core of many expert activities, such as fact-checking and hate speech, to counter harmful content. Yet, existing work treats counter-speech generation as pure text generation task, mainly based on Large Language Models or NGO experts. These approaches show severe drawbacks due to the limited reliability and coherence in the generated countering text, and in scalability, respectively. To close this gap, we introduce a novel framework to model counter-speech generation as knowledge-wise text generation process. Our framework integrates advanced Retrieval-Augmented Generation (RAG) pipelines to ensure the generation of trustworthy counter-speech for 8 main target groups identified in the hate speech literature, including women, people of colour, persons with disabilities, migrants, Muslims, Jews, LGBT persons, and other. We built a knowledge base over the United Nations Digital Library, EUR-Lex and the EU Agency for Fundamental Rights, comprising a total of 32,792 texts. We use the MultiTarget-CONAN dataset to empirically assess the quality of the generated counter-speech, both through standard metrics (i.e., JudgeLM) and a human evaluation. Results show that our framework outperforms standard LLM baselines and competitive approach, on both assessments. The resulting framework and the knowledge base pave the way for studying trustworthy and sound counter-speech generation, in hate speech and beyond.

Related papers

• On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation [88.77441715819366]
  Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content.<n>We propose a variety of likelihood- and generative-based evaluation methods that serve in place of naive global token perplexity.
  arXiv  Detail & Related papers  (2026-01-09T22:01:56Z)
• ParliaBench: An Evaluation and Benchmarking Framework for LLM-Generated Parliamentary Speech [0.2446948464551684]
  Parliamentary speeches require not only linguistic quality but also political authenticity and ideological consistency.<n>Current language models lack specialized training for parliamentary contexts.<n>We present ParliaBench, a benchmark for parliamentary speech generation.
  arXiv  Detail & Related papers  (2025-11-11T13:43:09Z)
• Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models [49.1574468325115]
  We introduce Speech-IFeval, an evaluation framework designed to assess instruction-following capabilities.<n>Recent SLMs integrate speech perception with large language models (LLMs), often degrading textual capabilities due to speech-centric training.<n>Our findings show that most SLMs struggle with even basic instructions, performing far worse than text-based LLMs.
  arXiv  Detail & Related papers  (2025-05-25T08:37:55Z)
• CODEOFCONDUCT at Multilingual Counterspeech Generation: A Context-Aware Model for Robust Counterspeech Generation in Low-Resource Languages [1.9263811967110864]
  This paper introduces a context-aware model for robust counterspeech generation, which achieved significant success in the MCG-COLING-2025 shared task.<n>By leveraging a simulated annealing algorithm fine-tuned on multilingual datasets, the model generates factually accurate responses to hate speech.<n>We demonstrate state-of-the-art performance across four languages, with our system ranking first for Basque, second for Italian, and third for both English and Spanish.
  arXiv  Detail & Related papers  (2025-01-01T03:36:31Z)
• PANDA -- Paired Anti-hate Narratives Dataset from Asia: Using an LLM-as-a-Judge to Create the First Chinese Counterspeech Dataset [3.8227015675440192]
  Despite prevalence of Modern Standard Chinese language, counterspeech resources for Chinese remain virtually nonexistent.<n>We introduce the a corpus that focuses on combating hate speech in Mainland China.
  arXiv  Detail & Related papers  (2025-01-01T01:56:32Z)
• Towards Unsupervised Speech Recognition Without Pronunciation Models [57.222729245842054]
  In this article, we tackle the challenge of developing ASR systems without paired speech and text corpora.<n>We experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling.<n>This innovative model surpasses the performance of previous unsupervised ASR models under the lexicon-free setting.
  arXiv  Detail & Related papers  (2024-06-12T16:30:58Z)
• Outcome-Constrained Large Language Models for Countering Hate Speech [10.434435022492723]
  This study aims to develop methods for generating counterspeech constrained by conversation outcomes. We experiment with large language models (LLMs) to incorporate into the text generation process two desired conversation outcomes. Evaluation results show that our methods effectively steer the generation of counterspeech toward the desired outcomes.
  arXiv  Detail & Related papers  (2024-03-25T19:44:06Z)
• Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF [14.2594830589926]
  Counterspeech, defined as a response to online hate speech, is increasingly used as a non-censorial solution. Our study introduces CoARL, a novel framework enhancing counterspeech generation by modeling the pragmatic implications underlying social biases in hateful statements. CoARL's first two phases involve sequential multi-instruction tuning, teaching the model to understand intents, reactions, and harms of offensive statements, and then learning task-specific low-rank adapter weights for generating intent-conditioned counterspeech.
  arXiv  Detail & Related papers  (2024-03-15T08:03:49Z)
• PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models [72.57329554067195]
  ProxyQA is an innovative framework dedicated to assessing longtext generation. It comprises in-depth human-curated meta-questions spanning various domains, each accompanied by specific proxy-questions with pre-annotated answers. It assesses the generated content's quality through the evaluator's accuracy in addressing the proxy-questions.
  arXiv  Detail & Related papers  (2024-01-26T18:12:25Z)
• Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models [86.02610674750345]
  Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks. We apply 14 adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations. All the language models and robust training methods we tested perform poorly on AdvGLUE, with scores lagging far behind the benign accuracy.
  arXiv  Detail & Related papers  (2021-11-04T12:59:55Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.