# Weak Supervision for Improved Precision in Search Systems

arXiv: https://arxiv.org/abs/2503.07025 · HTML: https://mlsanity.com/paper/2503.07025/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 10 of 10)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Horovod: fast and easy distributed deep learning in TensorFlow](https://mlsanity.com/paper/1802.05799/) (2018)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Learning the Structure of Generative Models without Labeled Data](https://mlsanity.com/paper/1703.00854/) (2017)
- [TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank](https://mlsanity.com/paper/1812.00073/) (2018)
- [Consistency of weighted majority votes](https://mlsanity.com/paper/1312.0451/) (2013)
- [The Matthew effect in empirical data](https://mlsanity.com/paper/1408.5124/) (2014)

## Abstract (arXiv)

Labeled datasets are essential for modern search engines, which increasingly rely on supervised learning methods like Learning to Rank and massive amounts of data to power deep learning models. However, creating these datasets is both time-consuming and costly, leading to the common use of user click and activity logs as proxies for relevance. In this paper, we present a weak supervision approach to infer the quality of query-document pairs and apply it within a Learning to Rank framework to enhance the precision of a large-scale search system.