CWF: A Collaborative Writing Framework for Personalized and Reliable Popular Science Writing

2026-09-05

AI Summary

为解决科学普及写作中个性化与准确性之间的矛盾，本文通过构建数据集、提出DA-MoE模型及多代理事实核查机制来提高文本适应性和可靠性。

Abstract

We introduce Personalized and Reliable Popular Science Writing, a novel task that requires adapting scientific explanations to audiences with different cognitive levels while preserving factual accuracy. However, improving personalization often introduces simplifications that increase the risk of hallucination and factual distortion. To address these challenges, we first construct a dataset of 39,134 entries and a reader-centric Personalized Science Communication Benchmark (PSCB) that jointly evaluates audience adaptation and factual accuracy. To reduce data and computational requirements while improving generalization across domains and audiences, we introduce DA-MoE, which explicitly decouples audience adaptation from domain knowledge through separate modeling. To enable robust verification and revision in evidence-scarce scenarios, a multi-agent fact-checking mechanism that augments limited evidence with role-specific agent debate and propagates confidence over a graph is proposed. Experiments on PSCB show that our approach achieves state-of-the-art performance. Our code is open-sourced at https://github.com/DPInnovationWorks/CWF.

Problem

• Personalized Science Writing
• Factual Accuracy
• Audience Adaptation
• Cognitive Levels
• Hallucination

Innovation

• CWF
• DA-MoE
• multi-agent fact-checking