Adversarial Text Generation using Large Language Models for Dementia Detection
Youxiang Zhu, Nana Lin, Kiran Balivada, Daniel Haehn, Xiaohui Liang
摘要
Although large language models (LLMs) excel in various text classification tasks, regular prompting strategies (e.g., few-shot prompting) do not work well with dementia detection via picture description. The challenge lies in the language marks for dementia are unclear, and LLM may struggle with relating its internal knowledge to dementia detection. In this paper, we present an accurate and interpretable classification approach by Adversarial Text Generation (ATG), a novel decoding strategy that could relate dementia detection with other tasks. We further develop a comprehensive set of instructions corresponding to various tasks and use them to guide ATG, achieving the best accuracy of 85%, >10% improvement compared to the regular prompting strategies. In addition, we introduce feature context, a humanunderstandable text that reveals the underlying features of LLM used for classifying dementia. From feature contexts, we found that dementia detection can be related to tasks such as assessing attention to detail, language, and clarity with specific features of the environment, character, and other picture content or languagerelated features. Future work includes incorporating multi-modal LLMs to interpret speech and picture information. Table 7: Linguistic-based instruction 21930 Discuss anything notable in the above text. Include as much detail as possible.<|eot_id|><|start_header_id|>assistant<|end_header_id|> What a chaotic scene you've described! Here are some notable points to discuss: Kitchen Mayhem * The stool is falling over, which suggests that it's either old, unstable, or has been poorly maintained. This adds to the sense of chaos in the kitchen. * The cookies being taken out of the cookie jar by the boy and being asked by the little girl to be handed to her quietly implies that snacking is a common activity in this household. * The fact that the stool is falling while the cookies are being handled increases the risk of mess and potential accidents. Sink Overflowing * The sink is overflowing, which means the mother is either taking a long time to wash dishes or isn't paying attention to the water level. This could be a source of stress or annoyance for her, but for now, she's choosing to dry dishes (on the assumption that it's less pressing). * This detail also creates a sense of water-themed tension, with water running "into" and possibly outside, but no indication of what happens to it. Wind Outside * The curtains are drawn back to allow a gentle breeze into the house, and the scene appears to be on a relatively mild day, as you mentioned. The fact that you explicitly state there's nothing to note about the outside action (beyond the path, window, and building envelope) suggests that the wind is likely a gentle, harmless blow. Kids' Actions * The girl's finger to the mouth could be seen as a clever play on innocence, hiding mischief behind a cookie-stealing facade. Her reach for a cookie and the brother's slippage from the stool create a sense of partnership in their naughtiness. * Both kids seem comfortable snacking in the kitchen, almost like it's a normalized behavior. Mother's Neglect (Daycare... er, laundry of attention?) * You cleverly contrast the overflowing sink with the mother's drying of dishes, implying a degree of obliviousness or prioritization on her part. Her feet getting soaked or compromised hygiene aren't necessarily consequences of her actions, but it does add to the impression of a household where multiple tasks are happening simultaneously. Summer Puddled Insight * Your aside about not knowing whether you meant for it to be action-worthy mentions several extraneous details, but effectively highlights the fact that the outside scene doesn't quite gel with the chaotic interior. You raise an interesting question about the importance of showing consequences or actions related to the stool tipping, overflowing water, or blowing curtains. * The comment about shortsightedly standing in the mother's attention ("um the mother or don't see much. um mother wiping dishes ") serves as a wry commentary on the scene's pandemonium. Overall, this vivid scene showcases a busy, potentially messy household where multiple dynamics are at play. The juxtaposition of controlled chaos (curtains flowing, kids snacking) with underlying mayhem (stool tipping, overflowing sink) creates a engaging contrast. The outside weather serves as a brief interlude, acknowledging that not everything has to be resolved or escalating inside Task: Analyze the Speaker's Clarity Objective: Evaluate the clarity of the speaker's description by assessing the ease of understanding the scene. Steps: 1. Break down the description into individual elements (actions, events, settings, characters). 2. Identify any sentences or phrases that are: * Concise and specific (Text-like) * Vague or open-ended (Script-like) * Overly descriptive (novelistic) * Redundant or unnecessary 3. Consider how thes
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper5
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 被引用 64,255 次
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 被引用 22,562 次
- Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford, Jong Wook Kim, Tao Xu, Greg Brockman 等ICML 2023 · 被引用 6,966 次
- Self-Instruct: Aligning Language Models with Self-Generated InstructionsYizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu 等ACL 2023 · 被引用 540 次
- A Tale of Two Perplexities: Sensitivity of Neural Language Models to Lexical Retrieval Deficits in Dementia of the Alzheimer's TypeTrevor Cohen, Serguei PakhomovACL 2020 · 被引用 2 次
相关 Paper
- DECT: Harnessing LLM-assisted Fine-Grained Linguistic Knowledge and Label-Switched and Label-Preserved Data Generation for Diagnosis of Alzheimer's DiseaseTingyu Mo, Jacqueline C. K. Lam, Victor O. K. Li, Lawrence Y. L. CheungAAAI 2025 · 被引用 4 次
- Delta-KNN: Improving Demonstration Selection in In-Context Learning for Alzheimer's Disease DetectionChuyuan Li, Raymond Li, Thalia Shoshana Field, Giuseppe CareniniACL 2025
- Localizing Active Objects from Egocentric Vision with Symbolic World KnowledgeTe-Lin Wu, Yu Zhou, Nanyun PengEMNLP 2023 · 被引用 5 次
- GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language ModelsChangye Li, David S. Knopman, Weizhe Xu, Trevor Cohen 等ACL 2022 · 被引用 24 次
- LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed PromptsHanan Gani, Shariq Farooq Bhat, Muzammal Naseer, Salman Khan 等ICLR 2024 · 被引用 61 次
