arXiv subjects

Viet Cuong Nguyen

Publications and source records attributed to Viet Cuong Nguyen.

8 recordsLinked to original sources

arXiv2026

CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking

Therapeutic dialogue is not a sequence of isolated responses: client goals, motivation, resistance, and therapeutic alliance evolve over time. Yet current LLM-based mental health dialogue systems often lack explicit mechanisms for tracking these dynamics across extended interactions, which can lead to poorly timed interventions or premature goal resolution. We introduce CALM-IT, a framework for generating and evaluating long-form Motivational Interviewing dialogues through explicit modeling of evolving client and counselor states, guiding both counseling strategy selection and utterance generation. We evaluate CALM-IT on a large-scale corpus of 8,232 synthetic dialogues spanning multiple dialogue lengths and frameworks. Compared with all baselines, CALM-IT achieves the best performance on most MITI 4.2 global ratings, including Empathy, Partnership, and Softening Sustain Talk, as well as on other key performance metrics while exhibiting minimal performance degradation as dialogue length increases. Notably, although CALM-IT initiates fewer change-directed prompts, it produces the highest client acceptance rate (64.3%) on average across different length conditions. We release a reproducible generation framework, a MITI-grounded process-level evaluation protocol, and a large-scale synthetic corpus for studying therapeutic LLMs under realistic long-form interaction conditions.

cs.CL↗

arXiv2025

Do Large Language Models Align with Core Mental Health Counseling Competencies?

The rapid evolution of Large Language Models (LLMs) presents a promising solution to the global shortage of mental health professionals. However, their alignment with essential counseling competencies remains underexplored. We introduce CounselingBench, a novel NCMHCE-based benchmark evaluating 22 general-purpose and medical-finetuned LLMs across five key competencies. While frontier models surpass minimum aptitude thresholds, they fall short of expert-level performance, excelling in Intake, Assessment & Diagnosis but struggling with Core Counseling Attributes and Professional Practice & Ethics. Surprisingly, medical LLMs do not outperform generalist models in accuracy, though they provide slightly better justifications while making more context-related errors. These findings highlight the challenges of developing AI for mental health counseling, particularly in competencies requiring empathy and nuanced reasoning. Our results underscore the need for specialized, fine-tuned models aligned with core mental health counseling competencies and supported by human oversight before real-world deployment. Code and data associated with this manuscript can be found at: https://github.com/cuongnguyenx/CounselingBench

cs.CL↗

arXiv2024

Supporters and Skeptics: LLM-based Analysis of Engagement with Mental Health (Mis)Information Content on Video-sharing Platforms

Over one in five adults in the US lives with a mental illness. In the face of a shortage of mental health professionals and offline resources, online short-form video content has grown to serve as a crucial conduit for disseminating mental health help and resources. However, the ease of content creation and access also contributes to the spread of misinformation, posing risks to accurate diagnosis and treatment. Detecting and understanding engagement with such content is crucial to mitigating their harmful effects on public health. We perform the first quantitative study of the phenomenon using YouTube Shorts and Bitchute as the sites of study. We contribute MentalMisinfo, a novel labeled mental health misinformation (MHMisinfo) dataset of 739 videos (639 from Youtube and 100 from Bitchute) and 135372 comments in total, using an expert-driven annotation schema. We first found that few-shot in-context learning with large language models (LLMs) are effective in detecting MHMisinfo videos. Next, we discover distinct and potentially alarming linguistic patterns in how audiences engage with MHMisinfo videos through commentary on both video-sharing platforms. Across the two platforms, comments could exacerbate prevailing stigma with some groups showing heightened susceptibility to and alignment with MHMisinfo. We discuss technical and public health-driven adaptive solutions to tackling the "epidemic" of mental health misinformation online.

cs.SI↗

arXiv2023

Understanding and Mitigating Mental Health Misinformation on Video Sharing Platforms

Despite the ever-strong demand for mental health care globally, access to traditional mental health services remains severely limited expensive, and stifled by stigma and systemic barriers. Thus, over the last few years, young people are increasingly turning to content on video-sharing platforms (VSPs) like TikTok and YouTube to help them navigate their mental health journey. However, navigating towards trustworthy information relating to mental health on these platforms is challenging, given the uncontrollable and unregulated growth of dedicated mental health content and content creators catering to a wide array of mental health conditions on these platforms. In this paper, we attempt to define what constitutes as "mental health misinformation" through examples. In addition, we also suggest some open questions to answer and challenges to tackle regarding this important and timely research topic

cs.SI↗

arXiv2018

Important descriptors and descriptor groups of Curie temperatures of rare-earth transition-metal binary alloys

We analyze Curie temperatures of rare-earth transition metal binary alloys with machine learning method. In order to select important descriptors and descriptor groups, we introduce newly developed subgroup relevance analysis and adopt the hierarchical clustering in the representation. We execute the exhaustive search and successfully illustrate the importance of descriptors and descriptor groups. We execute the exhaustive search and illustrate that our approach indeed leads to the successful selection of important descriptors and descriptor groups. It helps us to choose the combination of the descriptors and to understand the meaning of the selected combination of descriptors.

cond-mat.mtrl-sci↗

arXiv2017

A regression-based feature selection study of the Curie temperature of transition-metal rare-earth compounds: prediction and understanding

The Curie temperature ($T_C$) of binary alloy compounds consisting of 3$d$ transition-metal and 4$f$ rare-earth elements is analyzed by a machine learning technique. We first demonstrate that nonlinear regression can accurately reproduce $T_C$ of the compounds. The prediction accuracy for $T_C$ is maximized when five to ten descriptors are selected, with the rare-earth concentration being the most relevant. We then discuss an attempt to utilize a regression-based model selection technique to learn the relation between the descriptors and the actuation mechanism of the corresponding physical phenomenon, i.e., $T_C$ in the present case.

cond-mat.mtrl-sci↗

arXiv2011

Exotic leaky wave radiation from anisotropic epsilon near zero metamaterials

We investigate the emission of electromagnetic waves from biaxial subwavelength metamaterials. For tunable anisotropic structures that exhibit a vanishing dielectric response along a given axis, we find remarkable variation in the launch angles of energy associated with the emission of leaky wave radiation. We write closed form expressions for the energy transport velocity and corresponding radiation angle $ϕ$, defining the cone of radiation emission, both as a functions of frequency, and material and geometrical parameters. Full wave simulations exemplify the broad range of directivity that can be achieved in these structures.

physics.optics↗

arXiv2010

Total transmission and total reflection by zero index materials

In this report, we achieved total transmission and reflection in a slab of zero index materials with defect(s). By controlling the defect's radius and dielectric constant, we can obtain total transmission and reflection of EM wave. The zero index materials, in this report, stand for materials with permittivity and permeability which are simultaneously equal to zero or so called matched impedance zero index materials. Along with theoretical calculations and simulation demonstrations, we also discuss about some possible applications for the proposed structure such as shielding or cloaking an object without restricting its view. We also suggest a way to control total transmission and reflection actively by using tunable refractive index materials such as liquid crystal and BST. The physics behind those phenomena is attributed to intrinsic properties of zero index materials: constant field inside zero index slab.

cond-mat.mtrl-sci↗