Beyond Plain Demos: A Demo-Centric Anchoring Paradigm for In-Context Learning in Alzheimer’s Disease Detection
Puzhen Su, Haoran Yin, Miao Yongzhu, Jintao Tang, Shasha Li, Ting Wang
Abstract
Detecting Alzheimer’s disease (AD) from narrative transcripts challenges large language models (LLMs): pre-training rarely covers this out-of-distribution task, and all transcript demos describe the same scene, producing highly homogeneous contexts. These factors cripple both the model’s built-in task knowledge (task cognition) and its ability to surface subtle, class-discriminative cues (contextual perception). Because cognition is fixed after pre-training, improving in-context learning (ICL) for AD detection hinges on enriching perception through better demonstration (demo) sets. We demonstrate that standard ICL quickly saturates, its demos lack diversity (context width) and fail to convey fine-grained signals (context depth), and that recent task vector (TV) approaches improve broad task adaptation by injecting TV into the LLMs
BibTeX
@inproceedings{aaai2026_beyondplaindemos,
title = {Beyond Plain Demos: A Demo-Centric Anchoring Paradigm for In-Context Learning in Alzheimer’s Disease Detection},
author = {Puzhen Su and Haoran Yin and Miao Yongzhu and Jintao Tang and Shasha Li and Ting Wang},
booktitle = {AAAI 2026},
year = {2026}
}