# RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering

arXiv: https://arxiv.org/abs/2010.10757 · HTML: https://mlsanity.com/paper/2010.10757/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering](https://mlsanity.com/paper/2106.05346/) (2021)
- [R2-D2: A Modular Baseline for Open-Domain Question Answering](https://mlsanity.com/paper/2109.03502/) (2021)
- [Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering](https://mlsanity.com/paper/2101.00294/) (2021)
- [Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study](https://mlsanity.com/paper/2106.03826/) (2021)
- [Learning with Instance Bundles for Reading Comprehension](https://mlsanity.com/paper/2104.08735/) (2021)
- [Simple and Efficient ways to Improve REALM](https://mlsanity.com/paper/2104.08710/) (2021)
- [Re-Examining Calibration: The Case of Question Answering](https://mlsanity.com/paper/2205.12507/) (2022)
- [Detrimental Contexts in Open-Domain Question Answering](https://mlsanity.com/paper/2310.18077/) (2023)
- [E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation](https://mlsanity.com/paper/2411.00437/) (2024)

## Abstract (arXiv)

State-of-the-art Machine Reading Comprehension (MRC) models for Open-domain Question Answering (QA) are typically trained for span selection using distantly supervised positive examples and heuristically retrieved negative examples. This training scheme possibly explains empirical observations that these models achieve a high recall amongst their top few predictions, but a low overall accuracy, motivating the need for answer re-ranking. We develop a simple and effective re-ranking approach (RECONSIDER) for span-extraction tasks, that improves upon the performance of large pre-trained MRC models. RECONSIDER is trained on positive and negative examples extracted from high confidence predictions of MRC models, and uses in-passage span annotations to perform span-focused re-ranking over a smaller candidate set. As a result, RECONSIDER learns to eliminate close false positive passages, and achieves a new state of the art on four QA tasks, including 45.5% Exact Match accuracy on Natural Questions with real user questions, and 61.7% on TriviaQA.