The mismatch between the growing demand for psychological counseling and the limited availability of services has motivated research into the application of Large Language Models (LLMs) in this domain. Consequently, there is a need for a robust and unified benchmark to assess the counseling competence of various LLMs. Existing works, however, are limited by unprofessional client simulation, static question-and-answer evaluation formats, and unidimensional metrics. These limitations hinder their effectiveness in assessing a model's comprehensive ability to handle diverse and complex clients. To address this gap, we introduce CARE-Bench, a dynamic and interactive automated benchmark. It is built upon diverse client profiles derived from real-world counseling cases and simulated according to expert guidelines. CARE-Bench provides a multidimensional performance evaluation grounded in established psychological scales. Using CARE-Bench, we evaluate several general-purpose LLMs and specialized counseling models, revealing their current limitations. In collaboration with psychologists, we conduct a detailed analysis of the reasons for LLMs' failures when interacting with clients of different types, which provides directions for developing more comprehensive, universal, and effective counseling models.

In this letter, the novel asymmetrict-GARCH(1,1) (ATGARCH(1,1)) model is proposed. By calculating the tail exponent (TE), it is discovered that the TE of the ATGARCH(1,1) distribution is smaller than the degree of freedom (dof) of its corresponding driving Student-t distribution. Actually, we get that the TE of the ATGARCH(1,1) distribution is jointly determined by the corresponding dof and its model parameters. Since the closed-form density functions of the ATGARCH(1,1) noises are unknown, the corresponding filtering problems are analyzed by the heuristic method. In the ATGARCH(1,1) noise cases, the simulation results show that our heuristic algorithm is superior to the standard Kalman filter (KF), the particle filter, and those robust KFs designed by the Student-t distribution models.

The Myers-Briggs Type Indicator (MBTI) is one of the most influential personality theories reflecting individual differences in thinking, feeling, and behaving. MBTI personality detection has garnered considerable research interest and has evolved significantly over the years. However, this task tends to be overly optimistic, as it currently does not align well with the natural distribution of population personality traits. Specifically, the self-reported labels in existing datasets result in data quality issues and the hard labels fail to capture the full range of population personality distributions. In this paper, we identify the task by constructing MBTIBench, the first manually annotated MBTI personality detection dataset with soft labels, under the guidance of psychologists. Our experimental results confirm that soft labels can provide more benefits to other psychological tasks than hard labels. We highlight the polarized predictions and biases in LLMs as key directions for future research.

In recent years, Large Language Models (LLMs) have made significant progress in emotional support dialogue.However, there are two major challenges for LLM-based support systems.First, users may be hesitant to fully disclose their emotions at the outset.Second, direct probing or excessive questioning can induce discomfort or even resistance.To bridge this gap, we propose COCOON, a proactive emotional support framework that leverages principles of active listening to uncover implicit user needs.We design a multi-stage data curation pipeline and an annotation mechanism for support strategies.Based on this framework, we build COCOON-Llama3, a fine-tuned large language model, and evaluate it using both standard metrics and psychological scales.Experimental results indicate that our model more effectively elicits implicit emotional needs and delivers empathetic support compared to existing baselines, suggesting its utility for building more inclusive emotional support dialogue systems.

Detecting depression through users’ social media posting history is crucial for enabling timely intervention; however, irrelevant content within these posts negatively impacts detection performance. Thus, it is crucial to extract pertinent content from users’ complex posting history. Current methods utilize frozen screening models, which can miss critical information and limit overall performance due to isolated screening and detection processes. To address these limitations, we propose E2-LPS End-to-End Learnable Psychiatric Scale Guided Risky Post Screening Model) for jointly training our screening model, guided by psychiatric scales, alongside the detection model. We employ a straight-through estimator to enable a learnable end-to-end screening process and avoid the non-differentiability of the screening process. Experimental results show that E2-LPS outperforms several strong baseline methods, and qualitative analysis confirms that it better captures users’ mental states than others.

To provide a wide range of services for global users, cloud providers tend to build geo-distributed regions all over the world. With the rapid growth of cloud services, massive workloads and inter-region traffic have been introduced to current cloud networks, resulting in huge expenditure. Therefore, it is essential for a cloud provider to carefully place tasks and transfer traffic among regions to minimize the total operating costs. Existing solutions typically focus on optimizing either placement costs (e.g., computing resources, and electricity) or bandwidth costs, and overlook performance metrics, which leads to increased overall operating costs or lower user QoS. To bridge the gap, this paper proposes Copo, a joint cost and performance optimization framework for tenant task placement in geo-distributed clouds. We first formalize the cost optimization problem as an undetermined multi-commodity flow problem which has never been studied before, and propose a graph transformation algorithm to reduce the complexity. Then we combine the cost optimization with the performance optimization as the final framework. The key idea of Copo is leveraging KKT conditions to transfer the bi-level optimization to a single level. To efficiently acquire the joint task placement and traffic transfer decisions, we leverage McCormick Envelope-based relaxation to design a randomized rounding-based approximation algorithm. Extensive experiments based on real-world data show the superior cost-efficiency and performance of Copo compared with state-of-the-art solutions.

As an increasing number of users share their lives and mental states on social media, many studies attempt to detect depression risk through social media videos using non-verbal cues like facial expressions, posture, gaze, and intonation from individual social media platforms, a proven effective field. However, these studies have focused on single-video level analysis to detect depression. These researches fail to capture the dynamic nature of social media streams and the complex, often gradual manifestation of depression. This limitation overlooks the comprehensive mental state of users, which can only be understood through their extended video histories. To address this, we introduce the Multimodal User-level Depression Detection Dataset (MUD3). MUD3 includes the long-term video histories of depressed users on social media platforms, containing user mental states across multiple videos and treating the video histories as a continuous social media stream. This allows us to model multiple videos at the user-level and analyze users' long-term mental states. MUD3 and supplementary materials are available at https://github.com/Syx1030/MUD3.

Bichen Wang, Yuzhe Zi, Yixin Sun, Yanyan Zhao, Bing Qin. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Mental health issues pose significant challenges worldwide, leading researchers to utilize computing techniques to analyze social media posts for early detection. Currently, Large Language Models (LLMs) represent advanced AI systems with exceptional language processing capabilities. However, their effectiveness depends on the use of appropriate prompts. The design of suitable prompts specifically for analyzing mental health issues remains underexplored. Drawing inspiration from psychiatrists who use psychiatric scales to assess mental health, we have developed scale-based chains of thought (Scale-CoT) prompts. These not only enhance the LLMs’ ability to detect mental health issues but also increase clarity and explainability by integrating professional scales. Furthermore, we demonstrate that the knowledge generated by LLMs can be effectively transferred to smaller models, resulting in a better-performing and more lightweight system. Our approach, which leverages psychiatric scales, outperforms existing methods. Our experiments indicate that combining traditional psychiatry with computational techniques is worthwhile and deserving of further research and exploration.

Depression impacts millions worldwide, with increasing efforts to use social media data for early detection and intervention. Traditional Risk Detection (TRD) uses a user’s complete posting history for predictions, while Early Risk Detection (ERD) seeks early detection in a user’s posting history, emphasizing the importance of prediction earliness. However, ERD remains relatively underexplored due to challenges in balancing accuracy and earliness, especially with evolving partial data. To address this, we introduce the Early Sensing Depression Model (ESDM), which comprises two modules classification with partial information module (CPI) and decision for classification moment module (DMC), alongside an early detection loss function. Experiments show ESDM outperforms benchmarks in both earliness and accuracy.

The objective of suicide risk detection on social media is to identify individuals who may attempt suicide and determine their suicide risk level based on their online behavior. Although data-driven learning models have been used to predict suicide risk levels, these models often lack theoretical support and explanation from psychiatric research. To address this issue, we propose the incorporation of professional psychiatric scales into research to provide theoretical support and explanations for our model. Our proposed Scale-based Neural Network (SNN) architecture aims to extract content associated with scales from the posting history of social media users to predict their suicide risk level. Additionally, our approach provides scale-based explanations for the model's predictions. Experimental results demonstrate that our proposed method outperforms several strong baseline methods and highlights the potential of combining psychiatric scales and computational techniques to improve suicide risk detection.