Metraipolis › archive › dc_960483d79fc1
A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement — arXiv:2609.14178
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14178
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:14:59.398Z
- SHA-256 of the archived text
b417f841cd8d052a2c0f7cd28eb00e9f59a5eaf116fee9324b043a894db3cfdb- Stable URL of this page
https://metraipolis.com/documento/dc_960483d79fc1
How to cite
A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement — arXiv:2609.14178 — arXiv (en), https://arxiv.org/abs/2609.14178 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_960483d79fc1 (Metraipolis archive dc_960483d79fc1, sha256 b417f841cd8d052a2c0f7cd28eb00e9f59a5eaf116fee9324b043a894db3cfdb)
BibTeX
@misc{dc960483d79fc1,
title = {A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement — arXiv:2609.14178},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14178},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_960483d79fc1; sha256 b417f841cd8d052a2c0f7cd28eb00e9f59a5eaf116fee9324b043a894db3cfdb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14178. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Computers and Society (cs.CY); Social and Information Networks (cs.SI). Pagina del lavoro: https://arxiv.org/abs/2609.14178 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T22:51:09.864Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).