Zhuang Chen

Jiale Cheng, Sahand Sabour, Hao Sun et al.

Due to the lack of human resources for mental health support, there is an increasing demand for employing conversational agents for support. Recent work has demonstrated the effectiveness of dialogue models in providing emotional support. As previous studies have demonstrated that seekers' persona is an important factor for effective support, we investigate whether there are benefits to modeling such information in dialogue models for support. In this paper, our empirical analysis verifies that persona has an important impact on emotional support. Therefore, we propose a framework for dynamically inferring and modeling seekers' persona. We first train a model for inferring the seeker's persona from the conversation history. Accordingly, we propose PAL, a model that leverages persona information and, in conjunction with our strategy-based controllable generation method, provides personalized emotional support. Automatic and manual evaluations demonstrate that PAL achieves state-of-the-art results, outperforming the baselines on the studied benchmark. Our code and data are publicly available at https://github.com/chengjl19/PAL.

Jinfeng Zhou, Zhuang Chen, Dazhen Wan et al.

In this paper, we present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters. Our CharacterGLM is designed for generating Character-based Dialogues (CharacterDial), which aims to equip a conversational AI system with character customization for satisfying people's inherent social desires and emotional needs. On top of CharacterGLM, we can customize various AI characters or social agents by configuring their attributes (identities, interests, viewpoints, experiences, achievements, social relationships, etc.) and behaviors (linguistic features, emotional expressions, interaction patterns, etc.). Our model outperforms most mainstream close-source large langauge models, including the GPT series, especially in terms of consistency, human-likeness, and engagement according to manual evaluations. We will release our 6B version of CharacterGLM and a subset of training data to facilitate further research development in the direction of character-based dialogue generation.

Ting Zhang, Zhuang Chen, Ming Zhong et al.

Emotion recognition in conversation, which aims to predict the emotion for all utterances, has attracted considerable research attention in recent years. It is a challenging task since the recognition of the emotion in one utterance involves many complex factors, such as the conversational context, the speaker's background, and the subtle difference between emotion labels. In this paper, we propose a novel framework which mimics the thinking process when modeling these factors. Specifically, we first comprehend the conversational context with a history-oriented prompt to selectively gather information from predecessors of the target utterance. We then model the speaker's background with an experience-oriented prompt to retrieve the similar utterances from all conversations. We finally differentiate the subtle label semantics with a paraphrasing mechanism to elicit the intrinsic label related knowledge. We conducted extensive experiments on three benchmarks. The empirical results demonstrate the superiority of our proposed framework over the state-of-the-art baselines.

Jinfeng Zhou, Zhuang Chen, Bo Wang et al.

Emotional support conversation (ESC) aims to provide emotional support (ES) to improve one's mental state. Existing works stay at fitting grounded responses and responding strategies (e.g., question), which ignore the effect on ES and lack explicit goals to guide emotional positive transition. To this end, we introduce a new paradigm to formalize multi-turn ESC as a process of positive emotion elicitation. Addressing this task requires finely adjusting the elicitation intensity in ES as the conversation progresses while maintaining conversational goals like coherence. In this paper, we propose Supporter, a mixture-of-expert-based reinforcement learning model, and well design ES and dialogue coherence rewards to guide policy's learning for responding. Experiments verify the superiority of Supporter in achieving positive emotion elicitation during responding while maintaining conversational goals including coherence.

Zhuang Chen, Dazhen Wan, Zhangkai Zheng et al.

While large language models show promise in mental healthcare, evaluating their therapeutic competence remains challenging due to the unstructured and longitudinal nature of counseling. We argue that current evaluation paradigms suffer from an unanchored defect, leading to two forms of instability: process drift, where unsteered client simulation wanders away from specific counseling goals, and standard drift, where static pointwise scoring lacks the stability for reliable judgment. To address this, we introduce Ps, a unified framework that calibrates the therapeutic competence of LLMs via trajectory-anchored tournaments. We first anchor the interaction trajectory in simulation, where clients precisely control the fluid consultation process to probe multifaceted capabilities. We then anchor the battle trajectory in judgments through an efficient Swiss-system tournament, utilizing dynamic pairwise battles to yield robust Elo ratings. Beyond ranking, we demonstrate that tournament trajectories can be transformed into credible reward signals, enabling on-policy reinforcement learning to enhance LLMs' performance. Extensive experiments validate the effectiveness of PsychePass and its strong consistency with human expert judgments.

Jinfeng Zhou, Yongkang Huang, Bosi Wen et al.

Character-based dialogue (aka role-playing) enables users to freely customize characters for interaction, which often relies on LLMs, raising the need to evaluate LLMs' character customization capability. However, existing benchmarks fail to ensure a robust evaluation as they often only involve a single character category or evaluate limited dimensions. Moreover, the sparsity of character features in responses makes feature-focused generative evaluation both ineffective and inefficient. To address these issues, we propose CharacterBench, the largest bilingual generative benchmark, with 22,859 human-annotated samples covering 3,956 characters from 25 detailed character categories. We define 11 dimensions of 6 aspects, classified as sparse and dense dimensions based on whether character features evaluated by specific dimensions manifest in each response. We enable effective and efficient evaluation by crafting tailored queries for each dimension to induce characters' responses related to specific dimensions. Further, we develop CharacterJudge model for cost-effective and stable evaluations. Experiments show its superiority over SOTA automatic judges (e.g., GPT-4) and our benchmark's potential to optimize LLMs' character customization. Our repository is at https://github.com/thu-coai/CharacterBench.

Wanli Li, Tieyun Qian, Yi Song et al.

Zero-shot Relation Triplet Extraction (ZeroRTE) aims to extract relation triplets from texts containing unseen relation types. This capability benefits various downstream information retrieval (IR) tasks. The primary challenge lies in enabling models to generalize effectively to unseen relation categories. Existing approaches typically leverage the knowledge embedded in pre-trained language models to accomplish the generalization process. However, these methods focus solely on fitting the training data during training, without specifically improving the model's generalization performance, resulting in limited generalization capability. For this reason, we explore the integration of bi-level optimization (BLO) with pre-trained language models for learning generalized knowledge directly from the training data, and propose a generative meta-learning framework which exploits the `learning-to-learn' ability of meta-learning to boost the generalization capability of generative models. Specifically, we introduce a BLO approach that simultaneously addresses data fitting and generalization. This is achieved by constructing an upper-level loss to focus on generalization and a lower-level loss to ensure accurate data fitting. Building on this, we subsequently develop three generative meta-learning methods, each tailored to a distinct category of meta-learning. Extensive experimental results demonstrate that our framework performs well on the ZeroRTE task. Our code is available at https://github.com/leeworry/TGM-MetaLearning.

Zhuang Chen, Jincenzi Wu, Jinfeng Zhou et al.

Theory of Mind (ToM) is the cognitive capability to perceive and ascribe mental states to oneself and others. Recent research has sparked a debate over whether large language models (LLMs) exhibit a form of ToM. However, existing ToM evaluations are hindered by challenges such as constrained scope, subjective judgment, and unintended contamination, yielding inadequate assessments. To address this gap, we introduce ToMBench with three key characteristics: a systematic evaluation framework encompassing 8 tasks and 31 abilities in social cognition, a multiple-choice question format to support automated and unbiased evaluation, and a build-from-scratch bilingual inventory to strictly avoid data leakage. Based on ToMBench, we conduct extensive experiments to evaluate the ToM performance of 10 popular LLMs across tasks and abilities. We find that even the most advanced LLMs like GPT-4 lag behind human performance by over 10% points, indicating that LLMs have not achieved a human-level theory of mind yet. Our aim with ToMBench is to enable an efficient and effective evaluation of LLMs' ToM capabilities, thereby facilitating the development of LLMs with inherent social intelligence.

June M. Liu, Mengxia Gao, Sahand Sabour et al.

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 challenges. This paper introduces a pipeline for synthesizing clinical interviews, resulting in 1,157 interactive dialogues (PsyInterview), and presents EmoScan, an LLM-based emotional disorder screening system. EmoScan distinguishes between coarse (e.g., anxiety or depressive disorders) and fine disorders (e.g., major depressive disorders) and conducts high-quality interviews. Evaluations showed that EmoScan exceeded the performance of base models and other LLMs like GPT-4 in screening emotional disorders (F1-score=0.7467). It also delivers superior explanations (BERTScore=0.9408) and demonstrates robust generalizability (F1-score of 0.67 on an external dataset). Furthermore, EmoScan outperforms baselines in interviewing skills, as validated by automated ratings and human evaluations. This work highlights the importance of scalable data-generative pipelines for developing effective mental health LLM tools.

Zhuang Chen, Yaru Cao, Guanqun Bi et al.

Emotional support conversation (ESC) helps reduce people's psychological stress and provide emotional value through interactive dialogues. Due to the high cost of crowdsourcing a large ESC corpus, recent attempts use large language models for dialogue augmentation. However, existing approaches largely overlook the social dynamics inherent in ESC, leading to less effective simulations. In this paper, we introduce SocialSim, a novel framework that simulates ESC by integrating key aspects of social interactions: social disclosure and social awareness. On the seeker side, we facilitate social disclosure by constructing a comprehensive persona bank that captures diverse and authentic help-seeking scenarios. On the supporter side, we enhance social awareness by eliciting cognitive reasoning to generate logical and supportive responses. Building upon SocialSim, we construct SSConv, a large-scale synthetic ESC corpus of which quality can even surpass crowdsourced ESC data. We further train a chatbot on SSConv and demonstrate its state-of-the-art performance in both automatic and human evaluations. We believe SocialSim offers a scalable way to synthesize ESC, making emotional care more accessible and practical.

Guanqun Bi, Zhuang Chen, Zhoufu Liu et al.

Automating structured clinical interviews could revolutionize mental healthcare accessibility, yet existing large language models (LLMs) approaches fail to align with psychiatric diagnostic protocols. We present MAGI, the first framework that transforms the gold-standard Mini International Neuropsychiatric Interview (MINI) into automatic computational workflows through coordinated multi-agent collaboration. MAGI dynamically navigates clinical logic via four specialized agents: 1) an interview tree guided navigation agent adhering to the MINI's branching structure, 2) an adaptive question agent blending diagnostic probing, explaining, and empathy, 3) a judgment agent validating whether the response from participants meet the node, and 4) a diagnosis Agent generating Psychometric Chain-of- Thought (PsyCoT) traces that explicitly map symptoms to clinical criteria. Experimental results on 1,002 real-world participants covering depression, generalized anxiety, social anxiety and suicide shows that MAGI advances LLM- assisted mental health assessment by combining clinical rigor, conversational adaptability, and explainable reasoning.

Shijing Zhu, Zhuang Chen, Guanqun Bi et al.

Large language models (LLMs) have shown promise in providing scalable mental health support, while evaluating their counseling capability remains crucial to ensure both efficacy and safety. Existing evaluations are limited by the static assessment that focuses on knowledge tests, the single perspective that centers on user experience, and the open-loop framework that lacks actionable feedback. To address these issues, we propose Ψ-Arena, an interactive framework for comprehensive assessment and optimization of LLM-based counselors, featuring three key characteristics: (1) Realistic arena interactions that simulate real-world counseling through multi-stage dialogues with psychologically profiled NPC clients, (2) Tripartite evaluation that integrates assessments from the client, counselor, and supervisor perspectives, and (3) Closed-loop optimization that iteratively improves LLM counselors using diagnostic feedback. Experiments across eight state-of-the-art LLMs show significant performance variations in different real-world scenarios and evaluation perspectives. Moreover, reflection-based optimization results in up to a 141% improvement in counseling performance. We hope PsychoArena provides a foundational resource for advancing reliable and human-aligned LLM applications in mental healthcare.

Zhuang Chen, Guanqun Bi, Wen Zhang et al.

Depression is a widespread mental disorder that affects millions worldwide. While automated depression assessment shows promise, most studies rely on limited or non-clinically validated data, and often prioritize complex model design over real-world effectiveness. In this paper, we aim to unveil the landscape of clinical depression assessment. We introduce C-MIND, a clinical neuropsychiatric multimodal diagnosis dataset collected over two years from real hospital visits. Each participant completes three structured psychiatric tasks and receives a final diagnosis from expert clinicians, with informative audio, video, transcript, and functional near-infrared spectroscopy (fNIRS) signals recorded. Using C-MIND, we first analyze behavioral signatures relevant to diagnosis. We train a range of classical models to quantify how different tasks and modalities contribute to diagnostic performance, and dissect the effectiveness of their combinations. We then explore whether LLMs can perform psychiatric reasoning like clinicians and identify their clear limitations in realistic clinical settings. In response, we propose to guide the reasoning process with clinical expertise and consistently improves LLM diagnostic performance by up to 10% in Macro-F1 score. We aim to build an infrastructure for clinical depression assessment from both data and algorithmic perspectives, enabling C-MIND to facilitate grounded and reliable research for mental healthcare.

Yi Feng, Jiaqi Wang, Wenxuan Zhang et al. · tencent-ai

Recent progress in large language models (LLMs) has opened new possibilities for mental health support, yet current approaches lack realism in simulating specialized psychotherapy and fail to capture therapeutic progression over time. Narrative therapy, which helps individuals transform problematic life stories into empowering alternatives, remains underutilized due to limited access and social stigma. We address these limitations through a comprehensive framework with two core components. First, INT (Interactive Narrative Therapist) simulates expert narrative therapists by planning therapeutic stages, guiding reflection levels, and generating contextually appropriate expert-like responses. Second, IMA (Innovative Moment Assessment) provides a therapy-centric evaluation method that quantifies effectiveness by tracking "Innovative Moments" (IMs), critical narrative shifts in client speech signaling therapy progress. Experimental results on 260 simulated clients and 230 human participants reveal that INT consistently outperforms standard LLMs in therapeutic quality and depth. We further demonstrate the effectiveness of INT in synthesizing high-quality support conversations to facilitate social applications.

Yi Feng, Mingyang Song, Jiaqi Wang et al.

Children with Autism Spectrum Disorder (ASD) often misunderstand social situations and struggle to participate in daily routines. Social Stories are traditionally crafted by psychology experts under strict constraints to address these challenges but are costly and limited in diversity. As Large Language Models (LLMs) advance, there's an opportunity to develop more automated, affordable, and accessible methods to generate Social Stories in real-time with broad coverage. However, adapting LLMs to meet the unique and strict constraints of Social Stories is a challenging issue. To this end, we propose SS-GEN, a Social Story GENeration framework with LLMs. Firstly, we develop a constraint-driven sophisticated strategy named StarSow to hierarchically prompt LLMs to generate Social Stories at scale, followed by rigorous human filtering to build a high-quality dataset. Additionally, we introduce quality assessment criteria to evaluate the effectiveness of these generated stories. Considering that powerful closed-source large models require very complex instructions and expensive API fees, we finally fine-tune smaller language models with our curated high-quality dataset, achieving comparable results at lower costs and with simpler instruction and deployment. This work marks a significant step in leveraging AI to personalize Social Stories cost-effectively for autistic children at scale, which we hope can encourage future research on special groups.

Jincenzi Wu, Zhuang Chen, Jiawen Deng et al.

Theory of mind (ToM) refers to humans' ability to understand and infer the desires, beliefs, and intentions of others. The acquisition of ToM plays a key role in humans' social cognition and interpersonal relations. Though indispensable for social intelligence, ToM is still lacking for modern AI and NLP systems since they cannot access the human mental state and cognitive process beneath the training corpus. To empower AI systems with the ToM ability and narrow the gap between them and humans, in this paper, we propose COKE: the first cognitive knowledge graph for machine theory of mind. Specifically, COKE formalizes ToM as a collection of 45k+ manually verified cognitive chains that characterize human mental activities and subsequent behavioral/affective responses when facing specific social circumstances. In addition, we further generalize COKE using LLMs and build a powerful generation model COLM tailored for cognitive reasoning. Experimental results in both automatic and human evaluation demonstrate the high quality of COKE, the superior ToM ability of COLM, and its potential to significantly enhance social applications.

Zhuang Chen, Qian He, Zhifei Mao et al.

Douyin, internationally known as TikTok, has become one of the most successful short-video platforms. To maintain its popularity, Douyin has to provide better Quality of Experience (QoE) to its growing user base. Understanding the characteristics of Douyin videos is thus critical to its service improvement and system design. In this paper, we present an initial study on the fundamental characteristics of Douyin videos based on a dataset of over 260 thousand short videos collected across three months. The characteristics of Douyin videos are found to be significantly different from traditional online videos, ranging from video bitrate, size, to popularity. In particular, the distributions of the bitrate and size of videos follow Weibull distribution. We further observe that the most popular Douyin videos follow Zifp's law on video popularity, but the rest of the videos do not. We also investigate the correlation between popularity metrics used for Douyin videos. It is found that the correlation between the number of views and the number of likes are strong, while other correlations are relatively low. Finally, by using a case study, we demonstrate that the above findings can provide important guidance on designing an efficient edge caching system.