Next Article in Journal
Research Progress and Design Considerations of High-Speed Current-Mode Driver ICs
Previous Article in Journal
Data Augmentation and Gloss-Based Siamese Network for Metaphor Recognition
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

MPSR: A Multi-Perspective Self-Reflection Framework for Public Opinion Report Generation

1
State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China
2
School of Data Science and Intelligent Media, Communication University of China, Beijing 100024, China
3
Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin 150001, China
4
School of Engineering, Santa Clara University, Santa Clara, CA 95053, USA
5
College of Economics and Management, Beijing University of Technology, Beijing 100124, China
6
Chongqing Research Institute, Beijing University of Technology, Chongqing 401121, China
*
Authors to whom correspondence should be addressed.
Electronics 2026, 15(2), 404; https://doi.org/10.3390/electronics15020404
Submission received: 13 December 2025 / Revised: 12 January 2026 / Accepted: 15 January 2026 / Published: 16 January 2026

Abstract

Crisis events generate massive information flows from diverse sources, which need to be consolidated into public opinion reports to enable timely response by governments and enterprises. Current LLMs, despite strong generation capabilities, fail to achieve perspective diversity, maintain factual consistency, and perform coherent high-level planning. To address these gaps, we propose MPSR: a multi-perspective self-reflection framework. Our framework first assigns diverse stakeholder personas to agents who independently generate initial writing plans from complementary viewpoints. Subsequently, a three-stage debate mechanism refines these plans by identifying conflicts, formulates resolution strategies, and produces a consensus plan, thereby enhancing factual consistency. Finally, we introduce a Report Fusion mechanism to synthesize reports across temporal batches, ensuring comprehensive event coverage. Extensive experiments demonstrate that MPSR significantly outperforms baselines, achieving Date F1 of 0.67, G-Eval of 4.54, and MiniCheck score of 79.43, which represent improvements of 17.5%, 70.0%, and 25.8% over the strongest baseline, respectively.
Keywords: public opinion reports; large language models; multi-perspective self-reflection; debate mechanism; report fusion public opinion reports; large language models; multi-perspective self-reflection; debate mechanism; report fusion

Share and Cite

MDPI and ACS Style

Yu, J.; Fan, W.; Xu, Y.; Feng, Y.; Luo, J.; Zhu, L.; Shen, H. MPSR: A Multi-Perspective Self-Reflection Framework for Public Opinion Report Generation. Electronics 2026, 15, 404. https://doi.org/10.3390/electronics15020404

AMA Style

Yu J, Fan W, Xu Y, Feng Y, Luo J, Zhu L, Shen H. MPSR: A Multi-Perspective Self-Reflection Framework for Public Opinion Report Generation. Electronics. 2026; 15(2):404. https://doi.org/10.3390/electronics15020404

Chicago/Turabian Style

Yu, Jinzheng, Weijian Fan, Yang Xu, Yifan Feng, Jia Luo, Ligu Zhu, and Hao Shen. 2026. "MPSR: A Multi-Perspective Self-Reflection Framework for Public Opinion Report Generation" Electronics 15, no. 2: 404. https://doi.org/10.3390/electronics15020404

APA Style

Yu, J., Fan, W., Xu, Y., Feng, Y., Luo, J., Zhu, L., & Shen, H. (2026). MPSR: A Multi-Perspective Self-Reflection Framework for Public Opinion Report Generation. Electronics, 15(2), 404. https://doi.org/10.3390/electronics15020404

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop