# QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization

arXiv: https://arxiv.org/abs/1909.00215 · HTML: https://mlsanity.com/paper/1909.00215/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2019.

## Built on by (most cited first, 9 of 9)

- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Can NLI Models Verify QA Systems' Predictions?](https://mlsanity.com/paper/2104.08731/) (2021)
- [CLEVE: Contrastive Pre-training for Event Extraction](https://mlsanity.com/paper/2105.14485/) (2021)
- [Learning with Instance Bundles for Reading Comprehension](https://mlsanity.com/paper/2104.08735/) (2021)
- [ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection](https://mlsanity.com/paper/2108.12229/) (2021)
- [Representation Learning for Conversational Data using Discourse Mutual Information Maximization](https://mlsanity.com/paper/2112.05787/) (2021)
- [Model Agnostic Answer Reranking System for Adversarial Question Answering](https://mlsanity.com/paper/2102.03016/) (2021)
- [Actor-Critic Network for Q&A in an Adversarial Environment](https://mlsanity.com/paper/2201.00455/) (2022)
- [Improving Lexical Embeddings for Robust Question Answering](https://mlsanity.com/paper/2202.13636/) (2022)

## Abstract (arXiv)

Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing systems are not good at distinguishing distractor sentences, which look related but do not actually answer the question. To address this problem, we propose QAInfomax as a regularizer in reading comprehension systems by maximizing mutual information among passages, a question, and its answer. QAInfomax helps regularize the model to not simply learn the superficial correlation for answering questions. The experiments show that our proposed QAInfomax achieves the state-of-the-art performance on the benchmark Adversarial-SQuAD dataset.