A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement

• URL: http://arxiv.org/abs/2609.14178v1
• Date: Sat, 12 Sep 2026 23:00:19 GMT
• Title: A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement
• Abstract summary: Counter-narratives can reduce polarization, fuel public distrusts, and strengthen extremist narratives.<n>We present a multi-stage agent-based framework for generating, refining, and evaluating CNs.<n> CNs are applied to pro-Russian hate and misinformation narratives on the war with Ukraine and adaptable to other domains.
• Score: 1.2599533416395763
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid diffusion of hate speech and misinformation on social networks challenges democratic societies, since direct suppression efforts may deepen polarization, fuel public distrusts, and strengthen extremist narratives. LLM-driven counter-narratives (CNs) offer a promising way to reduce those risks, yet their effectiveness depends on rhetorical and stylistic choices that remain poorly understood. We present a multi-stage agent-based framework for generating, refining, and evaluating CNs, applied to pro-Russian hate and misinformation narratives on the war with Ukraine and adaptable to other domains. A pilot experiment with human evaluators identifies effective technique style pairings, such as repetition with emotional framing enhancing persuasiveness. Building on these insights, we introduce a multi-agent refinement process that iteratively improves CNs for persuasiveness, emotional engagement, and shareability. After human validation confirmed improvement, an automated safety analysis shows that our refined CNs match or improve on expert-written counterspeech. A simulated experiment then shows that they reduce the perceived strength of pro-Russian narratives and consistently outperform a vanilla LLM baseline, highlighting a pathway toward scalable, narrative-specific interventions against hate speech and misinformation. Code and data accompanying this work are publicly available at https://github.com/carmelkron/inlg2026-counter-narratives.

Related papers

• Belief Cascades Drive Persuasion in LLM Agent Networks [71.17605142402785]
  We study how goal-directed persuaders shift elicited stances in networks of LLM agents grounded in real-world ego-network topologies.<n>We show that direct exposure reliably predicts next-round stance change in competing runs, and peer relays carry smaller but measurable influence.<n>These results argue for evaluating multi-agent persuasion as a trajectory- and exposure-level process.
  arXiv  Detail & Related papers  (2026-08-25T21:01:19Z)
• CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges [9.965670989893267]
  We introduce the first large-scale, expert-curated, multilingual dataset of dialogues tackling the intersection of hate and misinformation.<n> Covering five languages and targeting hate directed at seven marginalized groups, this novel resource enables the training and evaluation of more persuasive, factually grounded counterspeech models.
  arXiv  Detail & Related papers  (2026-06-18T15:32:14Z)
• Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation [9.965670989893267]
  Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization.<n>Given their scale, using Large Language Models to assist expert counterspeech has gained interest.<n>We bridge this gap by studying CS generation in contexts where both hate and misinformation co-occur.
  arXiv  Detail & Related papers  (2026-05-21T13:02:08Z)
• STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning [80.78140312980484]
  We propose language-driven stepwise trajectory redirection, termed as STRIDE.<n>We co-train a generator and a generative verifier using only outcome-based rewards, eliminating external annotations.<n> Experiments on diverse reasoning benchmarks show that STRIDE significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-13T11:04:31Z)
• When Agents Persuade: Propaganda Generation and Mitigation in LLMs [2.1621083698499644]
  LLMs can be exploited to produce manipulative material.<n>We analyze their outputs using two domain-specific models: one that classifies text as propaganda or non-propaganda, and another that detects rhetorical techniques of propaganda.<n>We find that fine-tuning significantly reduces their tendency to generate such content, with ORPO proving most effective.
  arXiv  Detail & Related papers  (2026-03-04T21:56:29Z)
• Extend Adversarial Policy Against Neural Machine Translation via Unknown Token [66.40609413186122]
  We propose the DexChar policy' that introduces character perturbations for the existing mainstream adversarial policy based on token substitution.<n>We also improve the self-supervised matching that provides feedback in RL to cater to the semantic constraints required during training adversaries.
  arXiv  Detail & Related papers  (2025-01-21T14:43:04Z)
• Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs [0.600808022072121]
  Collusion to the disadvantage of others has been identified as a central form of undesirable agent cooperation. The use of information hiding (steganography) in agent communications could render collusion practically undetectable. This underscores the need for evaluation frameworks to monitor and mitigate steganographic collusion capabilities.
  arXiv  Detail & Related papers  (2024-10-02T16:18:33Z)
• PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent [71.20471076045916]
  Propaganda plays a critical role in shaping public opinion and fueling disinformation.<n>Propainsight systematically dissects propaganda into techniques, arousal appeals, and underlying intent.<n>Propagaze combines human-annotated data with high-quality synthetic data.
  arXiv  Detail & Related papers  (2024-09-19T06:28:18Z)
• A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation [14.064465097974836]
  This paper proposes a novel approach to evaluate Counter Narrative (CN) generation using a Large Language Model (LLM) as an evaluator. We show that traditional automatic metrics correlate poorly with human judgements and fail to capture the nuanced relationship between generated CNs and human perception.
  arXiv  Detail & Related papers  (2024-06-21T15:11:33Z)
• Towards Imperceptible Document Manipulations against Neural Ranking Models [13.777462017782659]
  We propose a framework called Imperceptible DocumEnt Manipulation (IDEM) to produce adversarial documents. IDEM instructs a well-established generative language model, such as BART, to generate connection sentences without introducing easy-to-detect errors. We show that IDEM can outperform strong baselines while preserving fluency and correctness of the target documents.
  arXiv  Detail & Related papers  (2023-05-03T02:09:29Z)
• Characterizing the adversarial vulnerability of speech self-supervised learning [95.03389072594243]
  We make the first attempt to investigate the adversarial vulnerability of such paradigm under the attacks from both zero-knowledge adversaries and limited-knowledge adversaries. The experimental results illustrate that the paradigm proposed by SUPERB is seriously vulnerable to limited-knowledge adversaries.
  arXiv  Detail & Related papers  (2021-11-08T08:44:04Z)
• Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News [57.9843300852526]
  We introduce the more realistic and challenging task of defending against machine-generated news that also includes images and captions. To identify the possible weaknesses that adversaries can exploit, we create a NeuralNews dataset composed of 4 different types of generated articles. In addition to the valuable insights gleaned from our user study experiments, we provide a relatively effective approach based on detecting visual-semantic inconsistencies.
  arXiv  Detail & Related papers  (2020-09-16T14:13:15Z)

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.