# Reliable Evaluation Protocol for Low-Precision Retrieval

arXiv: https://arxiv.org/abs/2508.03306 · HTML: https://mlsanity.com/paper/2508.03306/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Builds on (most cited first, 12 of 12)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [A Survey on Model Compression for Large Language Models](https://mlsanity.com/paper/2308.07633/) (2023)
- [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://mlsanity.com/paper/2407.19669/) (2024)
- [Efficient Post-training Quantization with FP8 Formats](https://mlsanity.com/paper/2309.14592/) (2023)
- [Semi-supervised Question Retrieval with Gated Convolutions](https://mlsanity.com/paper/1512.05726/) (2015)
- [Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers](https://mlsanity.com/paper/2506.00054/) (2025)
- [M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type](https://mlsanity.com/paper/2502.18755/) (2025)
- [Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech](https://mlsanity.com/paper/2406.03953/) (2024)
- [Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2505.01043/) (2025)

## Abstract (arXiv)

Lowering the numerical precision of model parameters and computations is widely adopted to improve the efficiency of retrieval systems. However, when computing relevance scores between the query and documents in low-precision, we observe spurious ties due to the reduced granularity. This introduces high variability in the results based on tie resolution, making the evaluation less reliable. To address this, we propose a more robust retrieval evaluation protocol designed to reduce score variation. It consists of: (1) High-Precision Scoring (HPS), which upcasts the final scoring step to higher precision to resolve tied candidates with minimal computational cost; and (2) Tie-aware Retrieval Metrics (TRM), which report expected scores, range, and bias to quantify order uncertainty of tied candidates. Our experiments test multiple models with three scoring functions on two retrieval datasets to demonstrate that HPS dramatically reduces tie-induced instability, and TRM accurately recovers expected metric values. This combination enables a more consistent and reliable evaluation system for lower-precision retrievals.