# Fair Cognitive Impairment Detection Through Unlearning

arXiv: https://arxiv.org/abs/2606.18571 · HTML: https://mlsanity.com/paper/2606.18571/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 30)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [End-to-End Bias Mitigation by Modelling Biases in Corpora](https://mlsanity.com/paper/1909.06321/) (2019)
- [Change is Hard: A Closer Look at Subpopulation Shift](https://mlsanity.com/paper/2302.12254/) (2023)
- [Towards Debiasing NLU Models from Unknown Biases](https://mlsanity.com/paper/2009.12303/) (2020)
- [Learning from others' mistakes: Avoiding dataset biases without modeling them](https://mlsanity.com/paper/2012.01300/) (2020)
- [Detecting cognitive decline using speech only: The ADReSSo Challenge](https://mlsanity.com/paper/2104.09356/) (2021)
- [Artificial Intelligence, speech and language processing approaches to monitoring Alzheimer's Disease: a systematic review](https://mlsanity.com/paper/2010.06047/) (2020)
- [Two Directions for Clinical Data Generation with Large Language Models: Data-to-Label and Label-to-Data](https://mlsanity.com/paper/2401.06774/) (2023)
- [Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition](https://mlsanity.com/paper/2406.05065/) (2024)
- [Debiasing Masks: A New Framework for Shortcut Mitigation in NLU](https://mlsanity.com/paper/2210.16079/) (2022)
- [On the social bias of speech self-supervised models](https://mlsanity.com/paper/2406.04997/) (2024)
- [Connected Speech-Based Cognitive Assessment in Chinese and English](https://mlsanity.com/paper/2406.10272/) (2024)
- [Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding](https://mlsanity.com/paper/2210.07547/) (2022)
- [Robust Natural Language Understanding with Residual Attention Debiasing](https://mlsanity.com/paper/2305.17627/) (2023)
- [A Contrastive Learning Approach to Mitigate Bias in Speech Models](https://mlsanity.com/paper/2406.14686/) (2024)
- [CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech](https://mlsanity.com/paper/2407.13660/) (2024)
- [Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech](https://mlsanity.com/paper/2412.15772/) (2024)
- [Speech Unlearning](https://mlsanity.com/paper/2506.00848/) (2025)
- [A Digital Language Coherence Marker for Monitoring Dementia](https://mlsanity.com/paper/2310.09623/) (2023)
- [Reformulating NLP tasks to Capture Longitudinal Manifestation of Language Disorders in People with Dementia](https://mlsanity.com/paper/2310.09897/) (2023)
- [Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities](https://mlsanity.com/paper/2302.02852/) (2023)
- [Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis](https://mlsanity.com/paper/2407.14180/) (2024)
- [Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods](https://mlsanity.com/paper/2510.26038/) (2025)
- [Bias and Fairness in Self-Supervised Acoustic Representations for Cognitive Impairment Detection](https://mlsanity.com/paper/2603.02937/) (2026)

## Abstract (arXiv)

Mild Cognitive Impairment (MCI) is a medical condition characterized by a noticeable decline in memory, language, or thinking abilities. MCI detection from spontaneous speech is promising for scalable screening. However, learned models often exploit demographic cues correlated with labels, resulting in a large performance gap across subgroups. We present a multimodal framework that combines (i) cross-model fusion between modalities (speech, text, and image), and (ii) unlearning using gradient reversal that discourages the shared embedding from encoding task-irrelevant demographic attributes. Evaluated on the multilingual benchmarks TAUKADIAL and PREPARE, our method outperforms the state-of-the-art multilingual and multimodal baseline in MCI classification while substantially reducing the performance gap across patient subgroups (sex and language). We further analyze transfer across datasets, showing that demographic unlearning helps learn more robust representations for MCI detection.