# Fine-tuning Small Language Models as Efficient Enterprise Search Relevance Labelers

arXiv: https://arxiv.org/abs/2601.03211 · HTML: https://mlsanity.com/paper/2601.03211/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [Large language models can accurately predict searcher preferences](https://mlsanity.com/paper/2309.10621/) (2023)
- [A Theoretical Analysis of NDCG Type Ranking Measures](https://mlsanity.com/paper/1304.6480/) (2013)
- [InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval](https://mlsanity.com/paper/2301.01820/) (2023)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [TREC CAsT 2019: The Conversational Assistance Track Overview](https://mlsanity.com/paper/2003.13624/) (2020)
- [One-Shot Labeling for Automatic Relevance Estimation](https://mlsanity.com/paper/2302.11266/) (2023)
- [INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning](https://mlsanity.com/paper/2401.06532/) (2024)
- [Can We Use Large Language Models to Fill Relevance Judgment Holes?](https://mlsanity.com/paper/2405.05600/) (2024)
- [Large Language Models for Relevance Judgment in Product Search](https://mlsanity.com/paper/2406.00247/) (2024)
- [Synthetic Data Generation with Large Language Models for Personalized Community Question Answering](https://mlsanity.com/paper/2410.22182/) (2024)
- [RRADistill: Distilling LLMs' Passage Ranking Ability for Long-Tail Queries Document Re-Ranking on a Search Engine](https://mlsanity.com/paper/2410.18097/) (2024)
- [Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking](https://mlsanity.com/paper/2504.03947/) (2025)
- [DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation](https://mlsanity.com/paper/2404.02489/) (2024)
- [Criteria-Based LLM Relevance Judgments](https://mlsanity.com/paper/2507.09488/) (2025)

## Abstract (arXiv)

In enterprise search, building high-quality datasets at scale remains a central challenge due to the difficulty of acquiring labeled data. To resolve this challenge, we propose an efficient approach to fine-tune small language models (SLMs) for accurate relevance labeling, enabling high-throughput, domain-specific labeling comparable or even better in quality to that of state-of-the-art large language models (LLMs). To overcome the lack of high-quality and accessible datasets in the enterprise domain, our method leverages on synthetic data generation. Specifically, we employ an LLM to synthesize realistic enterprise queries from a seed document, apply BM25 to retrieve hard negatives, and use a teacher LLM to assign relevance scores. The resulting dataset is then distilled into an SLM, producing a compact relevance labeler. We evaluate our approach on a high-quality benchmark consisting of 923 enterprise query-document pairs annotated by trained human annotators, and show that the distilled SLM achieves agreement with human judgments on par with or better than the teacher LLM. Furthermore, our fine-tuned labeler substantially improves throughput, achieving 17 times increase while also being 19 times more cost-effective. This approach enables scalable and cost-effective relevance labeling for enterprise-scale retrieval applications, supporting rapid offline evaluation and iteration in real-world settings.