中文
相关论文

相关论文: Synthetic or Authentic? Building Mental Patient Si…

200 篇论文

A fundamental challenge in opinion dynamics research is the scarcity of real-world longitudinal opinion data, which complicates the validation of theoretical models. To address this, we propose a novel simulation framework using large…

计算机科学与博弈论 · 计算机科学 2026-02-16 Yulong He , Dutao Zhang , Sergey Kovalchuk , Pengyi Li , Artem Sedakov

Providing dialogue agents with a profile representation can improve their consistency and coherence, leading to better conversations. However, current profile-based dialogue datasets for training such agents contain either explicit profile…

计算与语言 · 计算机科学 2024-08-28 Daniela Occhipinti , Serra Sinem Tekiroglu , Marco Guerini

Patient simulators are gaining traction in mental health training by providing scalable exposure to complex and sensitive patient interactions. Simulating depressed patients is particularly challenging, as safety constraints and high…

The availability of realistic simulated corpora is of key importance for the future progress of distant speech recognition technology. The reliability, flexibility and low computational cost of a data simulation process may ultimately allow…

音频与语音处理 · 电气工程与系统科学 2017-11-28 Mirco Ravanelli , Piergiorgio Svaizer , Maurizio Omologo

Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approaches rely on demographic surveys, personality questionnaires, or short AI-led interviews as…

计算与语言 · 计算机科学 2026-02-25 Yu Li , Pranav Narayanan Venkit , Yada Pruksachatkun , Chien-Sheng Wu

Synthetic personas are widely used to condition large language models (LLMs) for social simulation, yet most personas are still constructed from coarse sociodemographic attributes or summaries. We revisit persona creation by introducing…

计算与语言 · 计算机科学 2026-01-27 Pranav Narayanan Venkit , Yu Li , Yada Pruksachatkun , Chien-Sheng Wu

Objective Structured Clinical Examinations (OSCEs) are essential for medical training, but they require significant resources, including professional actors and expert medical feedback. Although Large Language Models (LLMs) have introduced…

人机交互 · 计算机科学 2025-08-20 Henrik Voigt , Yurina Sugamiya , Kai Lawonn , Sina Zarrieß , Atsuo Takanishi

Long-term, open-domain dialogue capabilities are essential for chatbots aiming to recall past interactions and demonstrate emotional intelligence (EI). Yet, most existing research relies on synthetic, LLM-generated data, leaving open…

计算与语言 · 计算机科学 2025-02-20 Dong-Ho Lee , Adyasha Maharana , Jay Pujara , Xiang Ren , Francesco Barbieri

Developing artificial intelligence based assistive systems to aid Persons with Dementia (PwD) requires large amounts of training data. However, data collection poses ethical, legal, economic, and logistic issues. Synthetic data generation…

人工智能 · 计算机科学 2021-07-13 Muhammad Salman Shaukat , Bjarne Christian Hiller , Sebastian Bader , Thomas Kirste

Large language models (LLMs) have been increasingly adopted to support patients' healthcare-seeking in recent years. While prior patient-centered studies have examined the capabilities and experience of LLM-based tools in specific…

The development of AI for mental health is hindered by a lack of authentic therapy dialogues, due to strict privacy regulations and the fact that clinical sessions were historically rarely recorded. We present an LLM-driven pipeline that…

Access to longitudinal, individual-level data on work-life balance and wellbeing is limited by privacy, ethical, and logistical constraints. This poses challenges for reproducible research, methodological benchmarking, and education in…

机器学习 · 计算机科学 2025-12-30 Wafaa El Husseini

Synthetic clinical data are increasingly important for advancing AI in healthcare, given strict privacy constraints on real-world EHRs, limited availability of annotated rare-condition data, and systemic biases in observational datasets.…

机器学习 · 计算机科学 2025-09-16 Rumeng Li , Xun Wang , Hong Yu

Simulating dementia patients with large language models (LLMs) is challenging due to the need to jointly model cognitive impairment, emotional dynamics, and nonverbal behaviors over long conversations. We present DemMA, an expert-guided…

多智能体系统 · 计算机科学 2026-01-13 Yutong Song , Jiang Wu , Kazi Sharif , Honghui Xu , Nikil Dutt , Amir Rahmani

Although artificial intelligence (AI) agents are increasingly proposed to support potentially longitudinal health tasks, such as symptom management, behavior change, and patient support, most current implementations fall short of…

人工智能 · 计算机科学 2026-04-30 Georgianna Lin , Rencong Jiang , Noémie Elhadad , Xuhai "Orson" Xu

Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling. However, adapting LLMs to this high-risk safety-critical domain is hindered by the scarcity of real-world counseling data…

The ability of large language models (LLMs) to process and reason over long textual inputs is critical for a wide range of real-world applications. However, progress in this area is significantly constrained by the absence of high-quality,…

计算与语言 · 计算机科学 2025-09-05 Seganrasan Subramanian , Abhigya Verma

Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in mental health, is challenging. Privacy concerns restrict data…

计算与语言 · 计算机科学 2024-07-16 Ryan Louie , Ananjan Nandi , William Fang , Cheng Chang , Emma Brunskill , Diyi Yang

Objective: This paper introduces a patient simulator for scalable, automated evaluation of healthcare conversational agents, generating realistic, controllable interactions that systematically vary across medical, linguistic, and behavioral…

Creating effective dialogue systems for mental health support requires high-quality multi-turn counseling dialogue data, yet collecting real counselor-client conversations presents significant challenges, including privacy concerns, high…

计算与语言 · 计算机科学 2026-05-27 Huachuan Qiu , Zhenzhong Lan