COMMUNITY-CROSS-INSTRUCT: Unsupervised Instruction Generation for Aligning Large Language...

[PDF] arxiv.org

Y social: an llm-powered social media digital twin

G Rossetti, M Stella, R Cazabet, K Abramski… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper we introduce Y, a new-generation digital twin designed to replicate an online
social media platform. Digital twins are virtual replicas of physical systems that allow for …
被引用次数：3 相关文章 所有 2 个版本
[PDF] arxiv.org

Feelings about bodies: Emotions on diet and fitness forums reveal gendered stereotypes and body image concerns

C Sánchez, MD Chu, Z He, R Dorn, S Murray… - arXiv preprint arXiv …, 2024 - arxiv.org
The gendered expectations about ideal body types can lead to body image concerns,
dissatisfaction, and in extreme cases, disordered eating and other psychopathologies …
被引用次数：2 相关文章 所有 2 个版本
[PDF] arxiv.org

Improving and Assessing the Fidelity of Large Language Models Alignment to Online Communities

MD Chu, Z He, R Dorn, K Lerman - arXiv preprint arXiv:2408.09366, 2024 - arxiv.org
Large language models (LLMs) have shown promise in representing individuals and
communities, offering new ways to study complex social dynamics. However, effectively …
相关文章 所有 2 个版本
[PDF] arxiv.org

SubData: A Python Library to Collect and Combine Datasets for Evaluating LLM Alignment on Downstream Tasks

L Fröhling, P Bernardelle, G Demartini - arXiv preprint arXiv:2412.16783, 2024 - arxiv.org
With the release of ever more capable large language models (LLMs), researchers in NLP
and related disciplines have started to explore the usability of LLMs for a wide variety of …
相关文章 所有 2 个版本