# Unsupervised multiple choices question answering via universal corpus

arXiv: https://arxiv.org/abs/2402.17333 · HTML: https://mlsanity.com/paper/2402.17333/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference](https://mlsanity.com/paper/1808.05326/) (2018)
- [Phrase-Based & Neural Unsupervised Machine Translation](https://mlsanity.com/paper/1804.07755/) (2018)
- [Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering](https://mlsanity.com/paper/2005.00646/) (2020)
- [Learning how to Active Learn: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1708.02383/) (2017)
- [Unsupervised Question Answering by Cloze Translation](https://mlsanity.com/paper/1906.04980/) (2019)
- [Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering](https://mlsanity.com/paper/2004.11892/) (2020)
- [Large Language Models Are Neurosymbolic Reasoners](https://mlsanity.com/paper/2401.09334/) (2024)
- [Self-supervised Knowledge Triplet Learning for Zero-shot Question Answering](https://mlsanity.com/paper/2005.00316/) (2020)
- [DAGN: Discourse-Aware Graph Network for Logical Reasoning](https://mlsanity.com/paper/2103.14349/) (2021)
- [Knowledge-Driven Distractor Generation for Cloze-style Multiple Choice Questions](https://mlsanity.com/paper/2004.09853/) (2020)
- [Harvesting and Refining Question-Answer Pairs for Unsupervised QA](https://mlsanity.com/paper/2005.02925/) (2020)
- [A Survey for Efficient Open Domain Question Answering](https://mlsanity.com/paper/2211.07886/) (2022)
- [BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering](https://mlsanity.com/paper/1904.04969/) (2019)
- [Better Distractions: Transformer-based Distractor Generation and Multiple Choice Question Filtering](https://mlsanity.com/paper/2010.09598/) (2020)
- [Zero-shot Commonsense Question Answering with Cloze Translation and Consistency Optimization](https://mlsanity.com/paper/2201.00136/) (2022)
- [Unsupervised Multiple Choices Question Answering: Start Learning from Basic Knowledge](https://mlsanity.com/paper/2010.11003/) (2020)
- [Context Modeling with Evidence Filter for Multiple Choice Question Answering](https://mlsanity.com/paper/2010.02649/) (2020)

## Abstract (arXiv)

Unsupervised question answering is a promising yet challenging task, which alleviates the burden of building large-scale annotated data in a new domain. It motivates us to study the unsupervised multiple-choice question answering (MCQA) problem. In this paper, we propose a novel framework designed to generate synthetic MCQA data barely based on contexts from the universal domain without relying on any form of manual annotation. Possible answers are extracted and used to produce related questions, then we leverage both named entities (NE) and knowledge graphs to discover plausible distractors to form complete synthetic samples. Experiments on multiple MCQA datasets demonstrate the effectiveness of our method.