待翻譯：Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.25028v1 Announce Type: new Abstract: 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.
AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
--> [Submitted on 25 Aug 2026] Title:Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection View a PDF of the paper titled Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection, by Pardis Ranjbar-Noiey and 1 other authors View PDF HTML (experimental) Abstract: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. Comments: 16 pages, 1 figure, 19 tables. Under review at ACL Rolling Review Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2608.25028 [cs.CL] (or arXiv:2608.25028v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.25028 arXiv-issued DOI via DataCite (pending registration) Submission history From: Pardis Ranjbar-Noiey [view email] [v1] Tue, 25 Aug 2026 18:16:05 UTC (66 KB) Full-text links: Access Paper: View a PDF of the paper titled Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection, by Pardis Ranjbar-Noiey and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-08 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)