Article

Detecting Self-Repairs from Spontaneous Speech with Prompt Ablation Across LLMs and Fine-Tuned Encoder

2026-08-25

Abstract excerpt

Self-repairs, in-utterance revisions in which a speaker abandons and reformulates their speech, are a promising interpretable marker for speech-based cognitive screening. Detecting them automatically is difficult because a self-repair is defined by its relationship to surrounding speech rather than by fixed lexical cues. On the DementiaBank ADReSS corpus, we compared the capability of generative LLMs under a five-...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: e6932937-7ba8-5b65-9882-0175418947e4
DOI: 10.64898/2026.08.21.26360471

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Detecting Self-Repairs from Spontaneous Speech with Prompt Ablation Across LLMs and Fine-Tuned EncoderDOI 10.64898/2026.08.21.26360471Read

Linguistic and Acoustic Biomarkers from Simulated Speech Reveal Early Cognitive Impairment Patterns in Alzheimer’s DiseaseSemantic proximity Read

AI-based Speech Error Detection to Differentiate Primary Progressive Aphasia VariantsSemantic proximity Read

ConfidentNeuro: Conformal Prediction-Based Uncertainty Quantification for Hallucination Risk Scoring in LLM-Assisted Alzheimer's Clinical Decision SupportSemantic proximity Read

clickBrick Prompt Engineering: Optimizing Large Language Model Performance in Clinical PsychiatrySemantic proximity Read

Domain-adapted language model using reinforcement learning for various dementiasSemantic proximity Read

Automatic speech recognition alters diagnostic error and biomarker validity in AI-based dementia speech assessmentSemantic proximity Read

Text dialogue analysis Based ChatGPT for Primary Screening of Mild Cognitive ImpairmentSemantic proximity Read

Large Language Models in Alzheimer’s Care: Clinical Use Cases, Safety Challenges, and Implementation PathwaysSemantic proximity Read

Generating Alzheimer's Narratives Using Large Language ModelsSemantic proximity Read

Zero-shot extraction of seizure outcomes from clinical notes using generative pretrained transformersSemantic proximity Read

LeCoder: A Large-Scale Automated Coder for Coding Errors in Word Production TasksSemantic proximity Read

Enhancing Reliability in Large Language Models: Self-Detection of Hallucinations With Spontaneous Self-ChecksSemantic proximity Read