让科普写作更懂读者，同时保证不编造事实。
CWF: A Collaborative Writing Framework for Personalized and Reliable Popular Science Writing
- 用分离式模型分别处理受众认知水平和领域知识。
- 在3.9万条数据上实现最高准确率，显著降低错误生成。
- 适合需要精准科普、内容审核的媒体与教育机构。
我们提出个性化且可靠的科普写作新任务，要求根据不同认知水平的受众调整科学解释，同时保持事实准确性。但提升个性化常导致简化表述，增加幻觉与事实偏差风险。为此，我们构建了包含39,134条数据的语料库，并推出以读者为中心的个性化科学传播基准（PSCB），联合评估受众适配性与事实准确性。为降低数据与计算开销并增强跨领域、跨受众泛化能力，提出DA-MoE模型，通过独立建模实现受众适应与领域知识解耦。针对证据稀缺场景，设计多智能体事实核查机制，通过角色化智能体辩论补充有限证据，并基于图结构传播置信度。在PSCB上的实验表明，该方法达到当前最优性能。代码已开源：https://github.com/DPInnovationWorks/CWF。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。