# Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search

arXiv: https://arxiv.org/abs/2601.04646 · HTML: https://mlsanity.com/paper/2601.04646/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [SciFact-Open: Towards open-domain scientific claim verification](https://mlsanity.com/paper/2210.13777/) (2022)
- [InPars: Data Augmentation for Information Retrieval using Large Language Models](https://mlsanity.com/paper/2202.05144/) (2022)
- [Arctic-Embed 2.0: Multilingual Retrieval Without Compromise](https://mlsanity.com/paper/2412.04506/) (2024)
- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback](https://mlsanity.com/paper/2108.13454/) (2021)
- [Don't Use LLMs to Make Relevance Judgments](https://mlsanity.com/paper/2409.15133/) (2024)
- [Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval](https://mlsanity.com/paper/2204.02292/) (2022)
- [Search-Adaptor: Embedding Customization for Information Retrieval](https://mlsanity.com/paper/2310.08750/) (2023)
- [Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency](https://mlsanity.com/paper/2306.11550/) (2023)

## Built on by (most cited first, 2 of 2)

- [Query-aware routing for Cross-lingual performance gains in Encoders](https://mlsanity.com/paper/2610.02875/) (2026)
- [Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence](https://mlsanity.com/paper/2610.13277/) (2026)

## Abstract (arXiv)

Large-scale multi-tenant retrieval systems generate extensive query logs but lack curated relevance labels for effective domain adaptation, resulting in substantial underutilized "dark data." This challenge is compounded by the high cost of model updates, as jointly fine-tuning query and document encoders requires full corpus re-indexing, which is impractical in multi-tenant settings with thousands of isolated indices. We introduce DevRev-Search, a passage retrieval benchmark for technical customer support built via a fully automated pipeline. Candidate generation uses fusion across diverse sparse and dense retrievers, followed by an LLM-as-a-Judge for consistency filtering and relevance labeling. We further study and systematically evaluate index-preserving query-only adaptation strategies that fine-tune only the query-encoder while keeping the document indices fixed. Experiments on DevRev-Search, SciFact, and FiQA-2018 show that parameter-efficient fine-tuning of the query encoder delivers a remarkable quality-efficiency trade-off, enabling scalable and practical enterprise multi-tenant retrieval.