Metraipolis › archive › dc_3da2bbc65b2b

MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate — arXiv:2609.04841

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04841
License (as archived): CC0-1.0
Archived: 2026-10-16T22:26:42.416Z
SHA-256 of the archived text: 935d346aa94565939bdce64d3d2c0177c8d01132014fc7e7376264276259287a
Stable URL of this page: https://metraipolis.com/documento/dc_3da2bbc65b2b

How to cite

MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate — arXiv:2609.04841 — arXiv (en), https://arxiv.org/abs/2609.04841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3da2bbc65b2b (Metraipolis archive dc_3da2bbc65b2b, sha256 935d346aa94565939bdce64d3d2c0177c8d01132014fc7e7376264276259287a)

BibTeX

@misc{dc3da2bbc65b2b,
  title = {MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate — arXiv:2609.04841},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04841},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3da2bbc65b2b; sha256 935d346aa94565939bdce64d3d2c0177c8d01132014fc7e7376264276259287a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Media bias in news articles operates through subtle linguistic cues---loaded language, selective framing, and strategic omission---that resist single-model detection and have traditionally required large annotated corpora for supervised training. We ask whether structured multi-agent deliberation can serve as a principled, training-free alternative to supervised classification for this task. We introduce MABPD (Multi-Agent Bias Probing & Detection), a pipeline in which three specialized LLM agents analyze an article from complementary perspectives and resolve disagreements through a Structured Argument Debate (SAD) protocol. SAD implements a domain-motivated asymmetric burden of proof---biased claims without grounded textual evidence carry zero weight---combined with role-weighted voting and post-consensus verification, replacing task-specific supervised decision boundaries with explicit deliberative structure. Ablation confirms that this structured deliberation, not mere agent parallelism, drives performance: removing the debate module reduces F1 by up to 10.6 points. On the BABE benchmark (4,121 expert-annotated sentences), MABPD achieves 83.4% macro F1 on the held-out test split---within 0.7 percentage points (pp) of the supervised SOTA (MAGPIE, 84.1% macro F1; Horych et al., 2024)---without any task-specific training or threshold tuning on annotated data. Cross-dataset evaluation on the SemEval 2019 HyperPartisan corpus (644 articles) yields 75.0% zero-shot accuracy, within 7.2 pp of the supervised SOTA accuracy (82.2%; Kiesel et al. 2019), confirming transfer across annotation regimes. We release the full pipeline and evaluation code.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.04841 — 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 2026-10-16T22:18:11.535Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).