# zELO: ELO-inspired Training Method for Rerankers and Embedding Models

arXiv: https://arxiv.org/abs/2509.12541 · HTML: https://mlsanity.com/paper/2509.12541/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 14 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Built on by (most cited first, 5 of 5)

- [MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval](https://mlsanity.com/paper/2605.06132/) (2026)
- [LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2601.05192/) (2026)
- [Overview of the TalentCLEF 2026: Skill and Job Title Intelligence for Human Capital Management](https://mlsanity.com/paper/2606.31692/) (2026)
- [LAMAR: An Open Language-Aware Multilingual Alignment Reranker](https://mlsanity.com/paper/2607.22042/) (2026)
- [BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval](https://mlsanity.com/paper/2609.27213/) (2026)

## Abstract (arXiv)

We introduce a novel training methodology named zELO, which optimizes retrieval performance via the analysis that ranking tasks are statically equivalent to a Thurstone model. Based on the zELO method, we use unsupervised data in order train a suite of state-of-the-art open-weight reranker models: zerank-1 and zerank-1-small. These models achieve the highest retrieval scores in multiple domains, including finance, legal, code, and STEM, outperforming closed-source proprietary rerankers on both NDCG@10 and Recall. These models also demonstrate great versatility, maintaining their 0-shot performance on out-of-domain and private customer datasets. The training data included 112,000 queries and 100 documents per query, and was trained end-to-end from unannotated queries and documents in less than 10,000 H100-hours.