الملخص
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.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Tripto, N. I., Zhang, D. C., Nahar, M., & Lee, D. (2026). One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation. https://omanscience.com/ar/articles/one-model-is-not-a-crowd-multi-llm-and-aspect-conditioned-diverse-comment-generation
MLA 9
Tripto, Nafis Irtiza, et al. "One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation." https://omanscience.com/ar/articles/one-model-is-not-a-crowd-multi-llm-and-aspect-conditioned-diverse-comment-generation.
شيكاغو (المؤلف–التاريخ)
Tripto, Nafis Irtiza, Delvin Ce Zhang, Mahjabin Nahar, and Dongwon Lee. 2026. "One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation." https://omanscience.com/ar/articles/one-model-is-not-a-crowd-multi-llm-and-aspect-conditioned-diverse-comment-generation.
هارفارد
Tripto, N. I., Zhang, D. C., Nahar, M. and Lee, D. (2026) 'One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation', Available at: https://omanscience.com/ar/articles/one-model-is-not-a-crowd-multi-llm-and-aspect-conditioned-diverse-comment-generation.
فانكوفر
Tripto NI, Zhang DC, Nahar M, Lee D. One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation. https://omanscience.com/ar/articles/one-model-is-not-a-crowd-multi-llm-and-aspect-conditioned-diverse-comment-generation
IEEE
N. I. Tripto, D. C. Zhang, M. Nahar, and D. Lee, "One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation," https://omanscience.com/ar/articles/one-model-is-not-a-crowd-multi-llm-and-aspect-conditioned-diverse-comment-generation.