# Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models

arXiv: https://arxiv.org/abs/2506.09315 · HTML: https://mlsanity.com/paper/2506.09315/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 39 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 8 of 8)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation](https://mlsanity.com/paper/2305.16938/) (2023)
- [Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge](https://mlsanity.com/paper/2004.06833/) (2020)
- [To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection](https://mlsanity.com/paper/2008.01551/) (2020)
- [A Tale of Two Perplexities: Sensitivity of Neural Language Models to Lexical Retrieval Deficits in Dementia of the Alzheimer's Type](https://mlsanity.com/paper/2005.03593/) (2020)
- [GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Models](https://mlsanity.com/paper/2203.13397/) (2022)

## Built on by (most cited first, 1 of 1)

- [MMSE-Calibrated Few-Shot Prompting for Alzheimer's Detection](https://mlsanity.com/paper/2509.19926/) (2025)

## Abstract (arXiv)

Alzheimer's dementia (AD) is a neurodegenerative disorder with cognitive decline that commonly impacts language ability. This work extends the paired perplexity approach to detecting AD by using a recent large language model (LLM), the instruction-following version of Mistral-7B. We improve accuracy by an average of 3.33% over the best current paired perplexity method and by 6.35% over the top-ranked method from the ADReSS 2020 challenge benchmark. Our further analysis demonstrates that the proposed approach can effectively detect AD with a clear and interpretable decision boundary in contrast to other methods that suffer from opaque decision-making processes. Finally, by prompting the fine-tuned LLMs and comparing the model-generated responses to human responses, we illustrate that the LLMs have learned the special language patterns of AD speakers, which opens up possibilities for novel methods of model interpretation and data augmentation.