中文
相关论文

相关论文: Auditing Stealth Sycophancy in Mental-Health Dialo…

200 篇论文

Depression-diagnosis-oriented chat aims to guide patients in self-expression to collect key symptoms for depression detection. Recent work focuses on combining task-oriented dialogue and chitchat to simulate the interview-based depression…

人机交互 · 计算机科学 2025-08-21 Yiyang Gu , Yougen Zhou , Qin Chen , Ningning Zhou , Jie Zhou , Aimin Zhou , Liang He

Small language models (SLMs) have been increasingly deployed in edge devices and other resource-constrained settings. However, these models make confident mispredictions and produce unstable output, making them risky for factual and…

人工智能 · 计算机科学 2026-04-07 Adeyemi Adeseye , Aisvarya Adeseye , Hannu Tenhunen , Jouni Isoaho

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. However, their tendency to exhibit sycophantic behavior - excessively agreeing with or flattering users - poses…

计算与语言 · 计算机科学 2025-01-30 Lars Malmqvist

Recent advances in Retrieval-Augmented Generation (RAG) have enabled large language models (LLMs) to ground outputs in clinical evidence. However, connecting LLMs with external databases introduces the risk of contextual leakage: a subtle…

计算与语言 · 计算机科学 2026-03-17 Shaowei Guan , Yu Zhai , Hin Chi Kwok , Jiawei Du , Xinyu Feng , Jing Li , Harry Qin , Vivian Hui

Recent advancements in large language models (LLMs) have shown their potential across both general and domain-specific tasks. However, there is a growing concern regarding their lack of sensitivity, factual incorrectness in responses,…

计算与语言 · 计算机科学 2025-12-01 Vivek Kumar , Pushpraj Singh Rajawat , Eirini Ntoutsi

Empathy is critical to successful mental health support. Empathy measurement has predominantly occurred in synchronous, face-to-face settings, and may not translate to asynchronous, text-based contexts. Because millions of people use…

计算与语言 · 计算机科学 2020-09-18 Ashish Sharma , Adam S. Miner , David C. Atkins , Tim Althoff

Large language models (LLMs) are already being piloted for clinical use in hospital systems like NYU Langone, Dana-Farber and the NHS. A proposed deployment use case is psychotherapy, where a LLM-powered chatbot can treat a patient…

计算与语言 · 计算机科学 2024-10-10 Saadia Gabriel , Isha Puri , Xuhai Xu , Matteo Malgaroli , Marzyeh Ghassemi

Standard safety alignment optimizes Large Language Models (LLMs) for universal helpfulness and honesty, effectively instilling a rigid "Boy Scout" morality. While robust for general-purpose assistants, this one-size-fits-all ethical…

人工智能 · 计算机科学 2026-01-12 Cooper Lin , Maohao Ran , Yanting Zhang , Zhenglin Wan , Hongwei Fan , Yibo Xu , Yike Guo , Wei Xue , Jun Song

LLM agents have begun to appear as personal assistants, customer service bots, and clinical aides. While these applications deliver substantial operational benefits, they also require continuous access to sensitive data, which increases the…

密码学与安全 · 计算机科学 2025-09-30 Saswat Das , Jameson Sandler , Ferdinando Fioretto

Depressive and anxiety disorders are widespread, necessitating timely identification and management. Recent advances in Large Language Models (LLMs) offer potential solutions, yet high costs and ethical concerns about training data remain…

计算与语言 · 计算机科学 2025-01-28 June M. Liu , Mengxia Gao , Sahand Sabour , Zhuang Chen , Minlie Huang , Tatia M. C. Lee

The transition of Large Language Models (LLMs) from passive knowledge retrievers to autonomous clinical agents demands a shift in evaluation-from static accuracy to dynamic behavioral reliability. To explore this boundary in dentistry, a…

The lack of explainability using relevant clinical knowledge hinders the adoption of Artificial Intelligence-powered analysis of unstructured clinical dialogue. A wealth of relevant, untapped Mental Health (MH) data is available in online…

人工智能 · 计算机科学 2024-10-21 Sumit Dalal , Deepa Tilwani , Kaushik Roy , Manas Gaur , Sarika Jain , Valerie Shalin , Amit Sheth

Mental health disorders remain among the leading cause of disability worldwide, yet conditions such as depression, anxiety, and Post-Traumatic Stress Disorder (PTSD) are frequently underdiagnosed or misdiagnosed due to subjective…

计算与语言 · 计算机科学 2025-10-17 Jianfeng Zhu , Julina Maharjan , Xinyu Li , Karin G. Coifman , Ruoming Jin

Mental health disorders represent a burgeoning global public health challenge. While Large Language Models (LLMs) have demonstrated potential in psychiatric assessment, their clinical utility is severely constrained by benchmarks that lack…

人工智能 · 计算机科学 2026-02-04 Xiao Sun , Yuming Yang , Junnan Zhu , Jiang Zhong , Xinyu Zhou , Kaiwen Wei

Mental health remains a major public health concern, while access to timely psychological support is often limited. AI-based dialogue systems have emerged as promising tools to address these barriers, and recent advances in large language…

计算机与社会 · 计算机科学 2026-03-16 Daeun Lee , Dongje Yoo , Migyeong Yang , Jihyun An , Christine B. Cha , Jinyoung Han

The latest large language models (LLMs) such as ChatGPT, exhibit strong capabilities in automated mental health analysis. However, existing relevant studies bear several limitations, including inadequate evaluations, lack of prompting…

计算与语言 · 计算机科学 2024-10-03 Kailai Yang , Shaoxiong Ji , Tianlin Zhang , Qianqian Xie , Ziyan Kuang , Sophia Ananiadou

Shared decision-making (SDM) is necessary to achieve patient-centred care. Currently no methodology exists to automatically measure SDM at scale. This study aimed to develop an automated approach to measure SDM by using language modelling…

As large language models (LLMs) increasingly mediate emotionally sensitive conversations, especially in mental health contexts, their ability to recognize and respond to high-risk situations becomes a matter of public safety. This study…

Large language models increasingly fail in a way that scalar accuracy cannot diagnose: they produce a sound reasoning trace and then abandon it under social pressure or an authoritative hint. We argue that this is a control failure, not a…

人工智能 · 计算机科学 2026-04-09 Edward Y. Chang

Large Vision-Language Models (LVLMs) have shown significant capability in vision-language understanding. However, one critical issue that persists in these models is sycophancy, where models are unduly influenced by leading or deceptive…

人工智能 · 计算机科学 2025-10-24 Yunpu Zhao , Rui Zhang , Junbin Xiao , Changxin Ke , Ruibo Hou , Yifan Hao , Ling Li