# On Monotonic Aggregation for Open-domain QA

arXiv: https://arxiv.org/abs/2308.04176 · HTML: https://mlsanity.com/paper/2308.04176/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Builds on (most cited first, 11 of 11)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering](https://mlsanity.com/paper/2012.14610/) (2020)
- [UnitedQA: A Hybrid Approach for Open Domain Question Answering](https://mlsanity.com/paper/2101.00178/) (2021)
- [Open Domain Question Answering with A Unified Knowledge Interface](https://mlsanity.com/paper/2110.08417/) (2021)
- [Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings](https://mlsanity.com/paper/2205.02303/) (2022)
- [On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering](https://mlsanity.com/paper/2209.12944/) (2022)

## Built on by (most cited first, 1 of 1)

- [ECoRAG: Evidentiality-guided Compression for Long Context RAG](https://mlsanity.com/paper/2506.05167/) (2025)

## Abstract (arXiv)

Question answering (QA) is a critical task for speech-based retrieval from knowledge sources, by sifting only the answers without requiring to read supporting documents. Specifically, open-domain QA aims to answer user questions on unrestricted knowledge sources. Ideally, adding a source should not decrease the accuracy, but we find this property (denoted as "monotonicity") does not hold for current state-of-the-art methods. We identify the cause, and based on that we propose Judge-Specialist framework. Our framework consists of (1) specialist retrievers/readers to cover individual sources, and (2) judge, a dedicated language model to select the final answer. Our experiments show that our framework not only ensures monotonicity, but also outperforms state-of-the-art multi-source QA methods on Natural Questions. Additionally, we show that our models robustly preserve the monotonicity against noise from speech recognition. We publicly release our code and setting.