Metraipolis › archive › dc_e34bcbd4f6a5

Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric — arXiv:2609.18306

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18306
License (as archived)
CC0-1.0
Archived
2026-10-15T15:04:41.401Z
SHA-256 of the archived text
fb5c3e5f246c49c13529016baac1d7c31f00ee46bff6265e61cd7ebbb2f414b4
Stable URL of this page
https://metraipolis.com/documento/dc_e34bcbd4f6a5

How to cite

Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric — arXiv:2609.18306 — arXiv (en), https://arxiv.org/abs/2609.18306 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e34bcbd4f6a5 (Metraipolis archive dc_e34bcbd4f6a5, sha256 fb5c3e5f246c49c13529016baac1d7c31f00ee46bff6265e61cd7ebbb2f414b4)
BibTeX
@misc{dce34bcbd4f6a5,
  title = {Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric — arXiv:2609.18306},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18306},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e34bcbd4f6a5; sha256 fb5c3e5f246c49c13529016baac1d7c31f00ee46bff6265e61cd7ebbb2f414b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18306. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly deployed in applications involving interaction between agents, where their output plays a role in collective reasoning and decision-making processes. Despite significant research into the functioning of LLMs in such multi-agent systems, the processes of bias propagation in such systems are still a challenge. This work studies how biased opinions are propagated in the form of textual interaction in an environment of LLMs, in which a minority of agents maintain persistent extreme opinions, while the remaining agents iteratively update their beliefs through structured textual interactions. The findings show that even the presence of a small percentage of biased agents in such a system leads to significant shifts in the opinions of non-biased agents. It suggests that for the same percentage of biased agents, the shifts occur more quickly for the Llama~3.2 model when compared to a classical Friedkin-Johnsen (FJ) model. Further semantic analysis demonstrates that rhetorical consistency in textual explanations increases systematically with biased exposure and, importantly, is partially decoupled from numerical convergenumericalutral agents adopt the vocabulary employed by the biased agents even in configurations where their numerical opinion shifts remain moderate. The research helps explain how bias and language develop together in multi-agent language model ecosystems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.18306 — 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 2026-10-15T14:08:19.117Z 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).