Metraipolis › archive › dc_ca75dd8dbcbf

Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts — arXiv:2608.06123

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.06123
License (as archived): CC0-1.0
Archived: 2026-10-25T21:31:24.424Z
SHA-256 of the archived text: 336fca1b3b6ce55424c9051a4eafdc60311681904d93715da1d37452c8e1e36f
Stable URL of this page: https://metraipolis.com/documento/dc_ca75dd8dbcbf

How to cite

Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts — arXiv:2608.06123 — arXiv (en), https://arxiv.org/abs/2608.06123 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca75dd8dbcbf (Metraipolis archive dc_ca75dd8dbcbf, sha256 336fca1b3b6ce55424c9051a4eafdc60311681904d93715da1d37452c8e1e36f)

BibTeX

@misc{dcca75dd8dbcbf,
  title = {Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts — arXiv:2608.06123},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06123},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca75dd8dbcbf; sha256 336fca1b3b6ce55424c9051a4eafdc60311681904d93715da1d37452c8e1e36f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06123. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Measuring political bias in large language models (LLMs) remains challenging as it can manifest through subtle differences in framing, argumentation, and legal reasoning that are difficult to capture with a single metric. In this work, we introduce POLI-BIAS, a counterfactual framework for measuring whether LLMs treat legally equivalent conflict scenarios differently depending on the countries involved. POLI-BIAS compares responses to paired prompts in which country identities are systematically swapped across diverse geopolitical relationships, legal violations, and reasoning tasks. Rather than reducing bias to a single judgment, our framework decomposes response disparities into five interpretable dimensions, revealing how and where unequal treatment manifests. Across 5,600 prompt pairs and seven open-weight LLMs from diverse model families and sizes, we find that models treat countries in active conflict or tension less evenly than fictional or uncontested countries, describing, evaluating, and defending equivalent actions differently. Our results thus establish POLI-BIAS as a fine-grained framework for auditing political even-handedness in LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.06123 — 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 2026-10-25T21:24:38.277Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).