Saved in:
Bibliographic Details
Main Authors: Gupta, Vipul, Mohan, Shikhar, Kumar, Lakshya, Chitale, Pranjal, Begwani, Nikit, Singh, Amit, Varma, Manik
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.23572
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914591666077696
author Gupta, Vipul
Mohan, Shikhar
Kumar, Lakshya
Chitale, Pranjal
Begwani, Nikit
Singh, Amit
Varma, Manik
author_facet Gupta, Vipul
Mohan, Shikhar
Kumar, Lakshya
Chitale, Pranjal
Begwani, Nikit
Singh, Amit
Varma, Manik
contents In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval models based on Small Language Models (SLMs) such as Qwen3-Embedding-4B/8B set strong upper bounds on public benchmarks, their deployment in high-throughput, latency-sensitive environments remains impractical. In this paper, we present HARNESS-LM (HLM), a three-phase training framework for transferring the capabilities of large-scale retrievers into compact, cost-efficient models. The approach comprises: (1) training a high-performance reference ("teacher") retriever by fine-tuning a billion-parameter-scale SLM; (2) aligning query representations via an L2 objective to distill knowledge into a sub-600M parameter student encoder; and (3) applying a final contrastive refinement stage to optimize the student for retrieval performance. We also present a comprehensive empirical study of key design choices, including alignment objectives, embedding dimensionality, model scale, architecture, and optimization strategies, to identify configurations that are most effective in production settings. On a real-world Bing Ads evaluation benchmark, HLM recovers over 98% of the reference retriever's precision across multiple settings, while delivering up to 27x lower online query-encoder latency and 20x higher throughput on NVIDIA A100 GPUs. Online A/B testing on Bing Ads further shows a +1% Revenue, +0.6% Impression, and +0.4% Click uplift over the current ensemble of retrievers running in production with the deployed 190M parameter model, clearly highlighting the practical efficacy of the HLM recipe in a real-world sponsored search setting.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23572
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval
Gupta, Vipul
Mohan, Shikhar
Kumar, Lakshya
Chitale, Pranjal
Begwani, Nikit
Singh, Amit
Varma, Manik
Information Retrieval
Artificial Intelligence
Machine Learning
In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval models based on Small Language Models (SLMs) such as Qwen3-Embedding-4B/8B set strong upper bounds on public benchmarks, their deployment in high-throughput, latency-sensitive environments remains impractical. In this paper, we present HARNESS-LM (HLM), a three-phase training framework for transferring the capabilities of large-scale retrievers into compact, cost-efficient models. The approach comprises: (1) training a high-performance reference ("teacher") retriever by fine-tuning a billion-parameter-scale SLM; (2) aligning query representations via an L2 objective to distill knowledge into a sub-600M parameter student encoder; and (3) applying a final contrastive refinement stage to optimize the student for retrieval performance. We also present a comprehensive empirical study of key design choices, including alignment objectives, embedding dimensionality, model scale, architecture, and optimization strategies, to identify configurations that are most effective in production settings. On a real-world Bing Ads evaluation benchmark, HLM recovers over 98% of the reference retriever's precision across multiple settings, while delivering up to 27x lower online query-encoder latency and 20x higher throughput on NVIDIA A100 GPUs. Online A/B testing on Bing Ads further shows a +1% Revenue, +0.6% Impression, and +0.4% Click uplift over the current ensemble of retrievers running in production with the deployed 190M parameter model, clearly highlighting the practical efficacy of the HLM recipe in a real-world sponsored search setting.
title HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2605.23572