mlsanityData to 14 Oct 2026

Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection

arXiv 2608.25028 ↗First posted 25 Aug 2026cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Spoken-language analysis via prompt-based domain-adaptive models is a promising direction for low-resource, non-invasive dementia screening, but such models remain internally opaque. We study the interpretability of the Domain-Adapted models via Prompt-based Fine-tuning (DAPF) framework, which casts dementia detection as diagnosis-related masked-token prediction. We interpret DAPF and strong baselines using a variety of probing and analysis techniques, finding that DAPF achieved the best overall performance (accuracy=0.83 and macro-F1=0.83) with diagnosis most recoverable from its [MASK] representation. However, this representational advantage did not extend to token-level explanation faithfulness. DAPF attributions primarily reflected language task vocabulary, discourse markers, and transcription artifacts, with perturbation tests showing weak or negative effects. This suggests that its masked-token interface determines diagnosis information without producing faithful token-level explanations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 72 references that are in the map. First posted on arXiv 25 Aug 2026.

Builds on

37 of 72 references.

References · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  9. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  10. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  11. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
  12. 2019How Can We Know What Language Models Know?cited by 959
25 more
  1. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  2. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 876
  3. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  4. 2019Designing and Interpreting Probes with Control Taskscited by 640
  5. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  6. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
  7. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  8. 2016Understanding Neural Networks through Representation Erasurecited by 224
  9. 2021Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classificationcited by 183
  10. 2020A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarioscited by 171
  11. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 156
  12. 2021OpenPrompt: An Open-source Framework for Prompt-learningcited by 148
  13. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  14. 2020Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challengecited by 104
  15. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 87
  16. 2021Detecting cognitive decline using speech only: The ADReSSo Challengecited by 81
  17. 2021Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Modelscited by 76
  18. 2021PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domainscited by 61
  19. 2020Artificial Intelligence, speech and language processing approaches to monitoring Alzheimer's Disease: a systematic reviewcited by 29
  20. 2021Alzheimer's Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy Inputscited by 27
  21. 2023SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domainscited by 12
  22. 2024Clever Hans Effect Found in Automatic Detection of Alzheimer's Disease through Speechcited by 9
  23. 2025Evaluating Spoken Language as a Biomarker for Automated Screening of Cognitive Impairmentcited by 5
  24. 2020Explainable CNN-attention Networks (C-Attention Network) for Automated Detection of Alzheimer's Diseasecited by 4
  25. 2021Towards Interpretability of Speech Pause in Dementia Detection using Adversarial Learningcited by 3

Built on by

Not cited yet.