MACA：一种将可信大语言模型提炼为高效检索器的框架
MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers
AI总结：
MACA通过提炼可信LLM为高效检索器，提升检索准确率并减少LLM调用成本
摘要：
现代企业检索系统必须处理诸如"外国交易费用退款"和"最近的支票状态"等短而模糊的查询。在这些情况下，语义细微差别和元数据很重要，但每次查询使用大型语言模型（LLM）重新排序和人工标注成本很高。我们提出了元数据意识的跨模型对齐（MACA），它将一个校准的元数据意识LLM重新排序器提炼成一个紧凑的学生检索器，避免在线LLM调用。一个元数据意识的提示通过检查在排列下的一致性和对同义词的鲁棒性来验证教师的可信度，然后提供列表式分数、困难负样本和校准的相关性边缘。学生使用MACA的MetaFusion目标进行训练，该目标结合了元数据条件的排序损失和跨模型边距损失，使其学会将正确的答案推至与语义相似但主题、子主题或实体不匹配的候选者之上。在一家私营消费银行FAQ语料库和BankFAQs上，MACA教师在专有数据集上的准确率@1比MAFA基线高出5个点，在BankFAQs上高出3个点。MACA学生显著优于预训练编码器；例如，在专有语料库上，MiniLM的准确率@1从0.23提高到0.48，同时保持了无LLM调用的推理，并支持检索增强生成。
英文摘要：
Modern enterprise retrieval systems must handle short, underspecified queries such as ``foreign transaction fee refund'' and ``recent check status''. In these cases, semantic nuance and metadata matter but per-query large language model (LLM) re-ranking and manual labeling are costly. We present Metadata-Aware Cross-Model Alignment (MACA), which distills a calibrated metadata aware LLM re-ranker into a compact student retriever, avoiding online LLM calls. A metadata-aware prompt verifies the teacher's trustworthiness by checking consistency under permutations and robustness to paraphrases, then supplies listwise scores, hard negatives, and calibrated relevance margins. The student trains with MACA's MetaFusion objective, which combines a metadata conditioned ranking loss with a cross model margin loss so it learns to push the correct answer above semantically similar candidates with mismatched topic, sub-topic, or entity. On a proprietary consumer banking FAQ corpus and BankFAQs, the MACA teacher surpasses a MAFA baseline at Accuracy@1 by five points on the proprietary set and three points on BankFAQs. MACA students substantially outperform pretrained encoders; e.g., on the proprietary corpus MiniLM Accuracy@1 improves from 0.23 to 0.48, while keeping inference free of LLM calls and supporting retrieval-augmented generation.
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。
