发表机构
Chungnam National University; Data Intelligence Laboratory（忠南国立大学; 数据智能实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对生成式AI检索低效与缺来源验证问题，提出双组件MPR-CiteG框架，用多组合检索器高效检索，引用基础生成模块确保输出事实一致且有源可溯，经实验验证其有效性与可靠性，助力构建更可信准确的大语言模型。
AI 中文摘要
本文提出了MPR-CiteG框架，该框架在ScienceON AI挑战赛中获得第二名，解决了生成式人工智能中的两个基本挑战：检索效率低下和缺乏来源验证。我们提出了一个双组件系统MPR-CiteG，其中多组合检索器（MPR）有效地检索多样且相关的信息，而引用基础生成（CiteG）模块确保每个生成的输出在事实方面保持一致，并明确归因于其来源。MPR-CiteG朝着构建更值得信赖和准确的大语言模型迈出了重要一步，不仅能够生成信息，还能将其响应基于可靠证据，从而减轻模型幻觉等常见问题。在挑战数据集上的大量实验验证了我们方法的有效性和可靠性。我们的代码可在这个https URL上获取。
英文摘要
This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in generative AI: inefficient retrieval and the absence of source verification. We propose a dual-component system, termed MPR-CiteG, in which the Multi-Portfolio Retriever (MPR) efficiently retrieves diverse and relevant information, while the Citation-Grounded Generation (CiteG) module ensures that every generated output remains factually consistent and explicitly attributed to its source. MPR-CiteG represents a significant step toward building more trustworthy and accurate LLMs that are not only capable of generating information but also of grounding their responses in reliable evidence, thereby mitigating common issues like model hallucination. Extensive experiments on the challenge dataset validate the effectiveness and reliability of our approach. Our code is available at https://github.com/2noweyh/MPR-citeG.
Comments12 pages, 1 figure, 7 tables. The 1st International Workshop on Retrieval-Driven Generative AI & ScienceON AI Challenge 2025@CIKM
