arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.04643cs.CL
收藏

当检索优于生成:面向可扩展假新闻检测的稠密证据检索

When retrieval outperforms generation: Dense evidence retrieval for scalable fake news detection

School of Computer Science, University of Galway, Ireland(Galway大学计算机科学学院);Research Ireland Insight Centre and ADAPT Centre, University of Galway, Ireland(Galway大学爱尔兰研究洞察中心和ADAPT研究中心)

Alamgir Munir Qazi, John P. McCrae, Jamal Abdul Nasir

AI总结:

本文提出轻量级框架DeReC,用稠密检索加专门分类替代大语言模型生成解释进行事实核查,在RAWFC和LIAR-RAW上分别将运行时间降低95%和92%,并在RAWFC上以65.58%的F1分数超越最先进方法L-Defense。

摘要:

错误信息的泛滥要求事实核查系统既稳健又具备计算高效性。当前最先进的方法利用大语言模型(LLMs)生成解释性理由,但这些方法在实际部署中面临显著的计算障碍和幻觉风险。我们提出DeReC(Dense Retrieval Classification,稠密检索分类),这是一个轻量级框架,展示了通用文本嵌入如何在事实核查任务中有效替代基于自回归大语言模型的方法。通过将稠密检索与专门分类相结合,我们的系统在显著提高效率的同时实现了更好的准确率。DeReC在效率上优于生成解释的大语言模型,在RAWFC上将运行时间降低了95%(23分36秒对比454分12秒),在LIAR-RAW上降低了92%(134分14秒对比1692分23秒),展示了其在不同数据集规模上的有效性。在RAWFC数据集上,DeReC取得了65.58%的F1分数,超过了最先进方法L-Defense(61.20%)。我们的结果表明,精心设计的基于检索的系统可以在专门任务中达到或超过大语言模型的性能,同时在实际部署中显著更具实用性。

英文摘要:

The proliferation of misinformation necessitates robust yet computationally efficient fact verification systems. While current state-of-the-art approaches leverage Large Language Models (LLMs) for generating explanatory rationales, these methods face significant computational barriers and hallucination risks in real-world deployments. We present DeReC (Dense Retrieval Classification), a lightweight framework that demonstrates how general-purpose text embeddings can effectively replace autoregressive LLM-based approaches in fact verification tasks. By combining dense retrieval with specialized classification, our system achieves better accuracy while being significantly more efficient. DeReC outperforms explanation-generating LLMs in efficiency, reducing runtime by 95% on RAWFC (23 minutes 36 seconds compared to 454 minutes 12 seconds) and by 92% on LIAR-RAW (134 minutes 14 seconds compared to 1692 minutes 23 seconds), showcasing its effectiveness across varying dataset sizes. On the RAWFC dataset, DeReC achieves an F1 score of 65.58%, surpassing the state-of-the-art method L-Defense (61.20%). Our results demonstrate that carefully engineered retrieval-based systems can match or exceed LLM performance in specialized tasks while being significantly more practical for real-world deployment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑