Balancing Engagement and Polarization: Multi-Objective Alignment of News Content Using LLMs
Release time：22 January 2026
Jan
26
|
Time & Date
|
10:30 am
-
12:00 pm,
January
26,
2026
(Monday)
|
|
Venue
|
Room D504, Teaching Complex D Building
|
| TOPIC | Balancing Engagement and Polarization: Multi-Objective Alignment of News Content Using LLMs |
| TIME&DATE | 10:30 am -12:00 pm, January 26, 2026 (Monday) |
| Venue | Room D504, Teaching Complex D Building |
| Speaker |
Mengjie (Magie) Cheng Harvard Business School |
| Abstract | We study how media firms can use LLMs to generate news content that aligns with multiple objectives – making content more engaging while maintaining a preferred level of polarization/slant consistent with the firm’s editorial policy. Using news articles from The New York Times, we first show that more engaging human-written content tends to be more polarizing. Further, naively employing LLMs (with prompts or standard Direct Preference Optimization approaches) to generate more engaging content can also increase polarization. This has an important managerial and policy implication: using LLMs without building in controls for limiting slant can exacerbate news media polarization. We present a constructive solution to this problem based on the Multi-Objective Direct Preference Optimization (MODPO) algorithm, a novel approach that integrates Direct Preference Optimization with multi-objective optimization techniques. We build on open-source LLMs and develop a new language model that simultaneously makes content more engaging while maintaining a preferred editorial stance. Our model achieves this by modifying content characteristics strongly associated with polarization but that have a relatively smaller impact on engagement. Our approach and findings apply to other settings where firms seek to use LLMs for content creation to achieve multiple objectives, e.g., advertising and social media.ed account of aspiration-driven search and stakeholder management. |
| Biography | Mengjie (Magie) Cheng is currently a Ph.D. candidate in Marketing at Harvard Business School. Her research focuses on content marketing, digital marketing, and generative AI. She brings together economic principles and behavioral insights with large language models, machine learning, and causal inference to inform strategic marketing decisions in the digital era. Prior to her doctoral studies, she worked as a machine learning engineer on the Ads Ranking and Knowledge Graph teams at Facebook. She earned her B.S. in Finance from the Chu Kochen Honors College at Zhejiang University and her M.S. in Management Science and Engineering from Stanford University. |
