# Secret-Keeping in Question Answering

arXiv: https://arxiv.org/abs/2303.09067 · HTML: https://mlsanity.com/paper/2303.09067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [Measuring Forgetting of Memorized Training Examples](https://mlsanity.com/paper/2207.00099/) (2022)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)
- [Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets](https://mlsanity.com/paper/2204.00032/) (2022)
- [QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension](https://mlsanity.com/paper/2107.12708/) (2021)
- [Fine-Grained Spoiler Detection from Large-Scale Review Corpora](https://mlsanity.com/paper/1905.13416/) (2019)
- [Overlearning Reveals Sensitive Attributes](https://mlsanity.com/paper/1905.11742/) (2019)
- [A Survey on Machine Reading Comprehension Systems](https://mlsanity.com/paper/2001.01582/) (2020)
- [ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters](https://mlsanity.com/paper/1809.09528/) (2018)
- [No Intruder, no Validity: Evaluation Criteria for Privacy-Preserving Text Anonymization](https://mlsanity.com/paper/2103.09263/) (2021)
- ["Killing Me" Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism](https://mlsanity.com/paper/2101.05972/) (2021)
- [Playing to Learn, or to Keep Secret: Alternating-Time Logic Meets Information Theory](https://mlsanity.com/paper/2303.00067/) (2023)

## Abstract (arXiv)

Existing question-answering research focuses on unanswerable questions in the context of always providing an answer when a system candots but what about cases where a system bf should not answer a question. This can either be to protect sensitive users or sensitive information. Many models expose sensitive information under interrogation by an adversarial user. We seek to determine if it is possible to teach a question-answering system to keep a specific fact secret. We design and implement a proof-of-concept architecture and through our evaluation determine that while possible, there are numerous directions for future research to reduce system paranoia (false positives), information leakage (false negatives) and extend the implementation of the work to more complex problems with preserving secrecy in the presence of information aggregation.