Metraipolis › archive › dc_2c18669dbadb

One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation — arXiv:2609.33666

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33666
License (as archived)
CC0-1.0
Archived
2026-10-07T21:53:06.190Z
SHA-256 of the archived text
5ea2196bb2da599f733030ce9389321e88a2c04a139aa601ec95b0224ccbb210
Stable URL of this page
https://metraipolis.com/documento/dc_2c18669dbadb

How to cite

One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation — arXiv:2609.33666 — arXiv (en), https://arxiv.org/abs/2609.33666 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c18669dbadb (Metraipolis archive dc_2c18669dbadb, sha256 5ea2196bb2da599f733030ce9389321e88a2c04a139aa601ec95b0224ccbb210)
BibTeX
@misc{dc2c18669dbadb,
  title = {One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation — arXiv:2609.33666},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33666},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c18669dbadb; sha256 5ea2196bb2da599f733030ce9389321e88a2c04a139aa601ec95b0224ccbb210},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33666. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human communication on the internet is shaped by diverse perspectives, most visibly expressed in online comment spaces. As large language model (LLM)based AI agents begin to inhabit these spaces, a key question arises: whether synthetic comment threads can capture the diversity inherent in human discourse. This concern is increasingly important, as the growing presence of homogenized AI-generated content risks reducing diversity over time, potentially leading to model collapse and degrading the richness of digital communication. Inspired by the plurality of human crowds and the aspect-driven nature of discourse, we hypothesize that comment diversity is better approximated by combining multiple LLMs with aspect-conditioned generation. We formalize and evaluate this approach using models from different providers and introduce a framework that characterizes diversity across semantic, linguistic, and socio-pragmatic features along three axes: dispersion, coverage, and alignment. Using this framework, we conduct a large-scale study on over 2 million YouTube comments across multiple domains. Our results reveal that multi-LLM and aspect-conditioned generation better align with human comment distributions and such data remains viable under pretraining style curation and is effective for downstream tasks. Yet, human diversity remains unmatched. Overall, our findings provide a practical foundation for generating more diverse and socially grounded discourse in AI-mediated environments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.33666 — 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 2026-10-07T21:27:08.537Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).