MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers

📝 Original Info

• Title: MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers
• ArXiv ID: 2601.00926
• Date: 2026-01-01
• Authors: Satya Swaroop Gudipudi, Sahil Girhepuje, Ponnurangam Kumaraguru, Kristine Ma

📝 Abstract

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 metadataaware 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 Accura...

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)