MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gudipudi, Satya Swaroop, Girhepuje, Sahil, Kumaraguru, Ponnurangam, Ma, Kristine
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909980203941888
author Gudipudi, Satya Swaroop
Girhepuje, Sahil
Kumaraguru, Ponnurangam
Ma, Kristine
author_facet Gudipudi, Satya Swaroop
Girhepuje, Sahil
Kumaraguru, Ponnurangam
Ma, Kristine
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00926
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers
Gudipudi, Satya Swaroop
Girhepuje, Sahil
Kumaraguru, Ponnurangam
Ma, Kristine
Information Retrieval
Artificial Intelligence
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.
title MACA: A Framework for Distilling Trustworthy LLMs into Efficient Retrievers
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2601.00926