# RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble

arXiv: https://arxiv.org/abs/2010.00200 · HTML: https://mlsanity.com/paper/2010.00200/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review](https://mlsanity.com/paper/2107.02975/) (2021)
- [MS MARCO: Benchmarking Ranking Models in the Large-Data Regime](https://mlsanity.com/paper/2105.04021/) (2021)
- [BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning](https://mlsanity.com/paper/2407.17631/) (2024)
- [SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches](https://mlsanity.com/paper/2503.03703/) (2025)
- [Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis](https://mlsanity.com/paper/2606.10381/) (2026)
- [SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora](https://mlsanity.com/paper/2602.10908/) (2026)

## Abstract (arXiv)

In this paper, we report the results of our participation in the TREC-COVID challenge. To meet the challenge of building a search engine for rapidly evolving biomedical collection, we propose a simple yet effective weighted hierarchical rank fusion approach, that ensembles together 102 runs from (a) lexical and semantic retrieval systems, (b) pre-trained and fine-tuned BERT rankers, and (c) relevance feedback runs. Our ablation studies demonstrate the contributions of each of these systems to the overall ensemble. The submitted ensemble runs achieved state-of-the-art performance in rounds 4 and 5 of the TREC-COVID challenge.