# When to Fold'em: How to answer Unanswerable questions

Source: [When to Fold'em: How to answer Unanswerable questions](<https://www.sota2.com/research/paper/68fa69d21e209131cea2469e>)

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

Data updated: 2025-10-25T23:09:38.543Z

Authors: Marshall Ho, Zhipeng Zhou, Judith He

Published: 2021-05-01T19:08:40.000Z

## Abstract

We present 3 different question-answering models trained on the SQuAD2.0 dataset -- BIDAF, DocumentQA and ALBERT Retro-Reader -- demonstrating the improvement of language models in the past three years. Through our research in fine-tuning pre-trained models for question-answering, we developed a novel approach capable of achieving a 2% point improvement in SQuAD2.0 F1 in reduced training time. Our method of re-initializing select layers of a parameter-shared language model is simple yet empirically powerful.

## 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/2105.00328>)

[PDF](<https://arxiv.org/pdf/2105.00328.pdf>)