# Confidence-Calibrated Ensemble Dense Phrase Retrieval

arXiv: https://arxiv.org/abs/2306.15917 · HTML: https://mlsanity.com/paper/2306.15917/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 28 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Phrase Retrieval Learns Passage Retrieval, Too](https://mlsanity.com/paper/2109.08133/) (2021)
- [Legal and Political Stance Detection of SCOTUS Language](https://mlsanity.com/paper/2211.11724/) (2022)

## Abstract (arXiv)

In this paper, we consider the extent to which the transformer-based Dense Passage Retrieval (DPR) algorithm, developed by (Karpukhin et. al. 2020), can be optimized without further pre-training. Our method involves two particular insights: we apply the DPR context encoder at various phrase lengths (e.g. one-sentence versus five-sentence segments), and we take a confidence-calibrated ensemble prediction over all of these different segmentations. This somewhat exhaustive approach achieves start-of-the-art results on benchmark datasets such as Google NQ and SQuAD. We also apply our method to domain-specific datasets, and the results suggest how different granularities are optimal for different domains