# Unsupervised Evaluation for Question Answering with Transformers

Source: [Unsupervised Evaluation for Question Answering with Transformers](<https://www.sota2.com/research/paper/68fa687d1e209131cea1c468>)

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

Data updated: 2025-10-25T22:38:00.142Z

Authors: Lukas Muttenthaler, Isabelle Augenstein, Johannes Bjerva

Published: 2020-10-07T07:03:30.000Z

## Abstract

It is challenging to automatically evaluate the answer of a QA model at inference time. Although many models provide confidence scores, and simple heuristics can go a long way towards indicating answer correctness, such measures are heavily dataset-dependent and are unlikely to generalize. In this work, we begin by investigating the hidden representations of questions, answers, and contexts in transformer-based QA architectures. We observe a consistent pattern in the answer representations, which we show can be used to automatically evaluate whether or not a predicted answer span is correct. Our method does not require any labeled data and outperforms strong heuristic baselines, across 2 datasets and 7 domains. We are able to predict whether or not a model's answer is correct with 91.37% accuracy on SQuAD, and 80.7% accuracy on SubjQA. We expect that this method will have broad applications, e.g., in the semi-automatic development of QA datasets

## 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/2010.03222>)

[PDF](<https://arxiv.org/pdf/2010.03222.pdf>)