CiteGuard: 通过检索增强验证实现LLM的忠实引文归因
CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation
AI总结:
本文提出CiteGuard,通过检索增强验证提升LLM引文准确性,实现比基线模型高10个百分点的性能,达到68.1%的准确率,接近人类水平。
摘要:
大型语言模型(LLM)已成为科学写作的强大助手,但其生成文本的质量和可靠性仍存疑,尤其是引文准确性。本文将引文评估重新定义为引文归因对齐问题,提出CiteGuard框架,通过检索增强验证提升引文验证的忠实度。CiteGuard在CiteME基准测试中达到68.1%的准确率,接近人类水平,并能识别替代有效引文,展示跨领域引文归因的泛化能力。
英文摘要:
Large Language Models (LLMs) have emerged as powerful assistants for scientific writing. However, concerns remain about the quality and reliability of the generated text, including citation accuracy and faithfulness. While most recent work relies on methods such as LLM-as-a-Judge, the reliability of LLM-as-a-Judge alone is also in doubt. In this work, we reframe citation evaluation as a problem of citation attribution alignment, which assesses whether LLM-generated citations match those a human author would include for the same text. We propose CiteGuard, a retrieval-aware agent framework designed to provide more faithful grounding for citation validation. CiteGuard improves over the prior baseline by 10 percentage points and achieves up to 68.1% accuracy on the CiteME benchmark, approaching human performance (69.2%). It also identifies alternative valid citations and demonstrates generalization ability for cross-domain citation attribution. Our code is available at https://github.com/KathCYM/CiteGuard.
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。