Searcharxiv⌕ Search

arXiv subjects

Lucen Li

Publications and source records attributed to Lucen Li.

3 recordsLinked to original sources

Using LLM Agents to Evaluate Prosocial Interventions on Social Media Platforms

Social media platforms are a primary source of information for many users. Although research explores various interventions to promote prosocial content or demote harmful content on platforms, there are few systematic methods for evaluating competing intervention designs before conducting costly human-subject experiments. We develop a simulation-based evaluation pipeline built on the OASIS framework. We generate 13,835 LLM-based agents, each with a unique profile. Over 20 time steps, we expose them to real-world Twitter/X posts and let them comment, like, repost, or follow. We use those agents to systematically evaluate three interventions that increase exposure to verified news: adding content, upranking content, and celebrity source cues. All interventions significantly increase news engagement, with upranking news to prominent feed positions producing the largest effects. These effects hold across agents' gender, age, and education levels. We validate our injection treatment results against a comparable human-subject study and find strong directional alignment and similar dose-normalized efficiency. Our results suggest that LLM-based agent simulations can support early-stage evaluation of platform interventions before human-subject deployment, and upranking may be more effective than news volume or source.

cs.SI↗

Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models

The prevalence of harmful content on social media platforms poses significant risks to users and society, necessitating more effective and scalable content moderation strategies. Current approaches rely on human moderators, supervised classifiers, and large volumes of training data, and often struggle with scalability, subjectivity, and the dynamic nature of harmful content (e.g., violent content, dangerous challenge trends, etc.). To bridge these gaps, we utilize Large Language Models (LLMs) to undertake few-shot dynamic content moderation via in-context learning. Through extensive experiments on multiple LLMs, we demonstrate that our few-shot approaches can outperform existing proprietary baselines (Perspective and OpenAI Moderation) as well as prior state-of-the-art few-shot learning methods, in identifying harm. We also incorporate visual information (video thumbnails) and assess if different multimodal techniques improve model performance. Our results underscore the significant benefits of employing LLM based methods for scalable and dynamic harmful content moderation online.

cs.CL↗

AI-Powered Browsers Are Broadly Accurate News Summarizers That Reduce Political Bias and Negative Affect

Web browsers now provide AI-generated news summaries for millions of users. Despite their popularity and influence, we lack a systematic understanding of how these systems transform news before people read it. Through a large-scale audit, we investigate the factual accuracy of browser-based AI summarizers and how they alter the political bias, negative affect, and journalistic writing quality of news. Drawing on 13,777 articles from 15 U.S. news outlets, we evaluate their 41,331 summaries generated by three leading AI-powered browsers: Google Chrome (Gemini), Microsoft Edge (Copilot), and Perplexity Comet. We find that browser-based AI summarizers are broadly accurate. Furthermore, they consistently transform news by attenuating ideological bias, partisan stances, negativity, anger, and fear, while increasing clarity and reducing personal tone. With some variations, these patterns hold across browsers, outlet ideologies, and topics. Our findings identify AI-powered browsers as a new class of editorial intermediaries that systematically reshape news, with implications for democratic discourse and AI governance.

cs.CY↗