# What's in a Name? Answer Equivalence For Open-Domain Question Answering

Source: [What's in a Name? Answer Equivalence For Open-Domain Question Answering](<https://www.sota2.com/research/paper/68fa6ab41e209131cea29e26>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:31:18.149Z

Authors: Chenglei Si, Chen Zhao, Jordan Boyd-Graber

Published: 2021-09-11T14:26:25.000Z

## Abstract

A flaw in QA evaluation is that annotations often only provide one gold answer. Thus, model predictions semantically equivalent to the answer but superficially different are considered incorrect. This work explores mining alias entities from knowledge bases and using them as additional gold answers (i.e., equivalent answers). We incorporate answers for two settings: evaluation with additional answers and model training with equivalent answers. We analyse three QA benchmarks: Natural Questions, TriviaQA, and SQuAD. Answer expansion increases the exact match score on all datasets for evaluation, while incorporating it helps model training over real-world datasets. We ensure the additional answers are valid through a human post hoc evaluation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.05289>)

[PDF](<https://arxiv.org/pdf/2109.05289.pdf>)