# Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering

arXiv: https://arxiv.org/abs/1711.05116 · HTML: https://mlsanity.com/paper/1711.05116/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2017.

## Built on by (most cited first, 24 of 24)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods](https://mlsanity.com/paper/2204.03508/) (2022)
- [Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering](https://mlsanity.com/paper/2101.00294/) (2021)
- [Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering](https://mlsanity.com/paper/2108.02866/) (2021)
- [Check It Again: Progressive Visual Question Answering via Visual Entailment](https://mlsanity.com/paper/2106.04605/) (2021)
- [You Only Need One Model for Open-domain Question Answering](https://mlsanity.com/paper/2112.07381/) (2021)
- [Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study](https://mlsanity.com/paper/2106.03826/) (2021)
- [Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation](https://mlsanity.com/paper/2201.05088/) (2022)
- [Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework](https://mlsanity.com/paper/2110.08544/) (2021)
- [A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering](https://mlsanity.com/paper/2104.08443/) (2021)
- [Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization](https://mlsanity.com/paper/2110.04741/) (2021)
- [FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering](https://mlsanity.com/paper/2211.10147/) (2022)
- [ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains](https://mlsanity.com/paper/2210.08763/) (2022)
- [Towards Confident Machine Reading Comprehension](https://mlsanity.com/paper/2101.07942/) (2021)
- [Improving Long Text Understanding with Knowledge Distilled from Summarization Model](https://mlsanity.com/paper/2405.04955/) (2024)
- [Model Agnostic Answer Reranking System for Adversarial Question Answering](https://mlsanity.com/paper/2102.03016/) (2021)
- [Complementary Evidence Identification in Open-Domain Question Answering](https://mlsanity.com/paper/2103.11643/) (2021)
- [ReFIT: Relevance Feedback from a Reranker during Inference](https://mlsanity.com/paper/2305.11744/) (2023)
- [Answer Consolidation: Formulation and Benchmarking](https://mlsanity.com/paper/2205.00042/) (2022)
- [Multi-grained Evidence Inference for Multi-choice Reading Comprehension](https://mlsanity.com/paper/2310.18070/) (2023)
- [Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM](https://mlsanity.com/paper/2602.18693/) (2026)
- [KILDST: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information](https://mlsanity.com/paper/2301.07341/) (2023)
- [An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation](https://mlsanity.com/paper/2407.20083/) (2024)

## Abstract (arXiv)

A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. Existing methods usually extract answers from single passages independently. But some questions require a combination of evidence from across different sources to answer correctly. In this paper, we propose two models which make use of multiple passages to generate their answers. Both use an answer-reranking approach which reorders the answer candidates generated by an existing state-of-the-art QA model. We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer. Our models have achieved state-of-the-art results on three public open-domain QA datasets: Quasar-T, SearchQA and the open-domain version of TriviaQA, with about 8 percentage points of improvement over the former two datasets.