Metraipolis › archive › dc_fcbb8a1b5c15
Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection — arXiv:2609.18597
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18597
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:08:05.794Z
- SHA-256 of the archived text
b9633e92fbd4d1ef6edb3859438452e4cd64e58ddc99b30ca27308e236d6837f- Stable URL of this page
https://metraipolis.com/documento/dc_fcbb8a1b5c15
How to cite
Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection — arXiv:2609.18597 — arXiv (en), https://arxiv.org/abs/2609.18597 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fcbb8a1b5c15 (Metraipolis archive dc_fcbb8a1b5c15, sha256 b9633e92fbd4d1ef6edb3859438452e4cd64e58ddc99b30ca27308e236d6837f)
BibTeX
@misc{dcfcbb8a1b5c15,
title = {Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection — arXiv:2609.18597},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18597},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fcbb8a1b5c15; sha256 b9633e92fbd4d1ef6edb3859438452e4cd64e58ddc99b30ca27308e236d6837f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18597. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Propagation structures provide crucial evidence for fake news detection, yet existing approaches primarily rely on supervised GNN-based models, which require substantial labeled data and exhibit limited generalization. Although large language models (LLMs) exhibit strong reasoning capabilities, directly feeding them raw propagation graphs creates a significant modality mismatch and severe information overload, making structure-aware reasoning unreliable in zero-shot and few-shot settings. To bridge this gap, we propose MAGER, a multi-agent genetic evolution framework that automatically discovers meta-paths optimized for LLM reasoning. By compressing complex propagation graphs into informative subgraphs, the evolved meta-paths alleviate both information overload and modality mismatch, enabling frozen LLMs to perform structure-aware veracity reasoning. We further introduce a graph in-context learning strategy that retrieves semantically and structurally similar demonstrations to strengthen classification and reasoning. Extensive experiments show that MAGER substantially improves frozen LLMs as standalone fake news detectors in data-efficient settings. Our code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.18597 — 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 2026-10-15T14:08:19.265Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).