Metraipolis › archive › dc_56feb900e920

Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling — arXiv:2608.02618

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02618
License (as archived)
CC0-1.0
Archived
2026-10-31T12:15:23.322Z
SHA-256 of the archived text
011f558d6610954984d66cbfe2e2d42ca2360d9d65a48ff0568529e8df88aa93
Stable URL of this page
https://metraipolis.com/documento/dc_56feb900e920

How to cite

Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling — arXiv:2608.02618 — arXiv (en), https://arxiv.org/abs/2608.02618 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_56feb900e920 (Metraipolis archive dc_56feb900e920, sha256 011f558d6610954984d66cbfe2e2d42ca2360d9d65a48ff0568529e8df88aa93)
BibTeX
@misc{dc56feb900e920,
  title = {Beyond the Hivemind: Escaping LLM Homogeneity via Meta-Persona Anchoring and Sequential Temperature Scaling — arXiv:2608.02618},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02618},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_56feb900e920; sha256 011f558d6610954984d66cbfe2e2d42ca2360d9d65a48ff0568529e8df88aa93},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02618. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent studies have identified an ``Artificial Hivemind'' effect in Large Language Models (LLMs) causing models to converge on a narrow, homogenized consensus even for open questions. This semantic collapse limits the diversity of AI, resulting in high inter-response similarity ($\approx 0.80-0.90$) even under high-temperature sampling. In this paper, we propose a novel mitigation framework to increase diversity: Meta-Persona Anchoring combined with Filtered Temperature Scaling (FTS). Our approach utilizes a two-stage generation process: first, the model is prompted to self-select a unique, idiosyncratic persona to anchor its starting point; second, we apply a dual-stage sampling sieve, utilizing Top-$p$ filtering to preserve grammatical validity followed by extreme temperature scaling ($T \ge 4.0$) on the surviving candidates to explore the broadened probability distribution. We evaluate our method using the INFINITY-CHAT dataset on state-of-the-art open weight models under $\sim$20B parameters. Our results demonstrate a significant reduction in semantic convergence, with average pairwise cosine similarity dropping from ($\approx 0.85$) to ($\approx 0.65$). Our scheme achieves a majority of questions below the 0.7 threshold, effectively reducing the gap between artificial mode collapse and human-level typological diversity. We provide our implementation as an open-source framework to enable more diverse and creative AI deployments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.02618 — 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 2026-10-31T12:05:52.722Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).