Metraipolis › archive › dc_486dbf9f0d0c
Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection — arXiv:2609.19778
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19778
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:48:02.377Z
- SHA-256 of the archived text
1f43d76b06de16618d8588be0d1ba6b9757fc3d81e4f3a210255e28a13271d31- Stable URL of this page
https://metraipolis.com/documento/dc_486dbf9f0d0c
How to cite
Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection — arXiv:2609.19778 — arXiv (en), https://arxiv.org/abs/2609.19778 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_486dbf9f0d0c (Metraipolis archive dc_486dbf9f0d0c, sha256 1f43d76b06de16618d8588be0d1ba6b9757fc3d81e4f3a210255e28a13271d31)
BibTeX
@misc{dc486dbf9f0d0c,
title = {Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection — arXiv:2609.19778},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19778},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_486dbf9f0d0c; sha256 1f43d76b06de16618d8588be0d1ba6b9757fc3d81e4f3a210255e28a13271d31},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19778. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hateful memes spread abusive content through implicit interactions between images and text, posing serious threats to the safety of online communities. In recent years, multimodal large language models have been widely used for hateful meme detection and are increasingly adopted to generate explainable detection results. However, we find that existing explain-then-detect methods often couple explanation generation and label prediction within the same training process. This coupling causes interference between task objectives, leading to limited detection performance and even worse results than simple SFT baselines. To address these challenges, we propose ProKDA, a progressive knowledge-to-decision alignment method for explainable hateful meme detection. Inspired by the human annotation training process, ProKDA first uses an agentic background knowledge construction pipeline to obtain external knowledge related to meme understanding. It then adopts a three-stage training strategy that sequentially performs background knowledge learning, hatefulness detection learning, and hatefulness boundary alignment. Unlike prior explain-then-detect methods that jointly optimize both tasks, ProKDA focuses on a single training objective at each stage. This design reduces interference between the two tasks and progressively transforms background knowledge into robust detection decisions. Experiments on three public hateful meme benchmarks show that ProKDA achieves state-of-the-art detection performance and provides accurate, explainable, and evidence-supported decisions for hateful meme moderation. Project page: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.19778 — 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 2026-10-10T03:24:08.131Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).