DeepSupport, a multi-persona PS system trained with OrthoTune, a PS-tailored framework with style-specific adapters and a style-consistency regularizer is built, unifying the five DeepSupport personas into Ekova, a persistent personality-support agent with a unified cross-session memory layer, supporting both adaptive routing and user-customized persona selection.
Abstract
Emotional Support (ES) systems have long optimized a single objective: alleviating the user's emotional distress in the moment. We argue that a complementary need, helping users see themselves more clearly, defines a distinct paradigm we call Personality Support (PS). PS is not counseling or clinical intervention: it targets cognitive clarity and self-articulation, not symptom relief or diagnosis. We instantiate this paradigm in three layers. First, we present DSD, a Chinese self-discovery PS Dataset of 8,590 samples collected through real longitudinal interaction across five minimal units, Coach, Warm, Tsukkomi, Real, and Gonzo. Second, we build DeepSupport, a multi-persona PS system trained with OrthoTune, a PS-tailored framework with style-specific adapters and a style-consistency regularizer. Third, we unify the five DeepSupport personas into Ekova, a persistent personality-support agent with a unified cross-session memory layer, supporting both adaptive routing and user-customized persona selection. Experiments show that OrthoTune-trained models outperform all baselines with an average relative gain of 16.3% across all metrics over the strongest prompt-based baseline. Code is available at https://github.com/Yukyin/Ekova.
EmoTrace, a multi-turn dialogue corpus generation framework centered on modeling seekers' emotional trajectories, is proposed, which outperforms existing approaches in terms of emotional richness and empathy quality.
Kai-Tong Weng, Lixiong Liu, Zihao Liu et al.· arXiv.org· 0 citations
AI companions are judged not only by single-turn fluency but by whether they sustain emotional continuity: remembering who the companion is, what the user prefers, and how the relationship has felt. We present ZifaMem, a structured memory system that organizes dialogue into session summaries, episodic memories, and a consolidated user model. Against a deployment-honest comparator that supplies the full raw dialogue history, and under a fixed LLM-as-a-judge protocol with route audits, structured memory raises pooled four-backbone emotional-intelligence scores by 11.4% (95% CI 6.3% to 17.1%), and persona grounding improves on all four backbones (Claude +42% relative). Multi-turn affect context wins a +39% net preference over a single-turn snapshot (exploratory), whereas an additional emotion state machine yields no measurable gain on any of five endpoints. Under an identical preregistered protocol, three memory systems (ZifaMem, Mem0, and filtered verbatim retrieval) each improve significantly over raw-history deployment, and ZifaMem and Mem0 are statistically equivalent within +/-5 points on the preregistered primary preference endpoint. The ZifaMem SDK, CLI, and portable Agent Skills are open-sourced at https://github.com/zifacorp/zifamem.
Jingzhe Fang, Guozhi Xu, Yunfan Cui et al.· 0 citations
Linguistic-based anxiety screening has become a widely adopted approach for detecting anxiety in social media, with pre-trained language models (PLMs) now forming the state-of-the-art foundation for early mental health detection. However, most existing PLMs are not explicitly optimized for anxiety detection (AD), limiting their adaptability to fine-grained psycholinguistic cues. To address this gap, we introduce SOFIA (Anxious? SOFten-It-Out), a novel prompt-based reasoning framework that enhances PLM capability for binary AD without full fine-tuning. SOFIA integrates multiple prompt template strategies with a dual-end truncation method that preserves both initial contextual cues and concluding emotional markers, enabling richer and more stable representations of conversational anxiety signals. Additionally, a knowledge-enhanced verbalizer incorporates structured domain knowledge through soft, manual, and automatic verbalizers, improving reasoning within frozen PLMs. We evaluate SOFIA across three self-reported anxiety corpora, such as Guo, SMHD, and Kim, using multiple 100M−300M-parameter PLMs. Experimental results demonstrate consistent improvements over traditional baselines, including F1 score gains of 5.37%, 5.40%, and 7.92% for MentalBERT on the respective datasets when using soft templates of length 20 with knowledge base-driven verbalizers. These findings highlight SOFIA's effectiveness as a scalable, low-resource, and knowledge-informed framework for digital mental health screening applications.
A. Senanayake, Prasan Yapa, Sidath Liyanage· Frontiers in Digital Health· 0 citations
Effective human-AI interaction requires systems that dynamically adapt to a user's behavior and evolving understanding. When users interact with Large Language Models (LLMs), these models typically respond to prompts without sensing the user's immediate reactions. This lack of communicative synchrony can lead to information overload or leave confusion unresolved in real time. In this paper, we introduce Aura, a framework that enables LLM systems to dynamically modulate output based on a user's evolving emotions. Aura's Perception Module continuously estimates the user's emotional state from facial expressions. Our Policy Module then selects interventions through a probabilistic belief model. Finally, Aura's Generation Module uses parameter-efficient Low-Rank Adaptation (LoRA) adapters to produce contextually tailored responses mid-turn during response generation. We evaluated Aura in a within-subjects user study (N=20) on information-seeking tasks, where it achieved statistically significantly higher normalized perceived learning gains than a Llama-3 baseline and reduced interaction time by 21% relative to existing LLM baselines (GPT-4o, Llama-3). Our results indicate that real-time, context-sensitive interventions can improve learning efficiency and user satisfaction without observable degradation in factual accuracy. Aura thus supports the potential for more responsive and effective human-AI interaction.
Emotional dialogue research includes two influential strategy traditions. Empathetic dialogue prioritizes understanding a speaker's emotional experience. Emotional support conversation selects and sequences support for the seeker's current needs. Sustained use introduces a further goal. Effective support should sustain users'capacities for emotion regulation, coping, self-endorsed decisions, and social connection across the interaction lifecycle. We propose capability-sustaining emotional dialogue (CSED) as a longitudinal research paradigm that aligns supportive strategy with this goal and organizes data, models, system design, evaluation, and governance around repeated use, non-use, transition, and termination. A targeted literature-and-corpus audit motivates this position. In a PRISMA-ScR-guided sample, 95% of 60 system-building papers pursue relief-oriented goals. None evaluates capability or longitudinal outcomes, and only 1 considers dependency, autonomy, or termination risk. In 300 ESConv supporter turns, capability-relevant functions appear in 43.0%, while generic suggestions account for 22.0%, compared with 4.0% reappraisal, 6.7% self-efficacy support, and 0.3% boundary behavior. We release a protocol for extending the audit to model behavior. An illustrative process model connects latent user capability to six design commitments, four evaluation timescales, and lifecycle constraints. The resulting agenda makes CSED testable across data, policy design, training, evaluation, and governance.
Ming Wang, Jiaqi Wu Young, Wenfang Wu et al.· arXiv.org· 0 citations
Despite advances in Emotional Intelligence (EI), Large Language Models (LLMs) still significantly underperform humans in complex emotional reasoning. This gap originates partly from the limited incorporation of individual differences, particularly personality traits, which are fundamental to human emotional inference. To address this, we propose PTEI, a novel framework for integrating Personality Traits into Emotional Intelligence tasks using LLMs. In PTEI, MBTI and OCEAN personality traits are first extracted directly from the given emotional scenarios and then utilized as contextual knowledge within personality-aware prompts, guiding LLMs to accurately infer emotions and their underlying causes. To ensure optimal contextual grounding, we employ Contrastive Learning to construct an optimized retrieval system that surfaces emotionally and personally aligned scenarios, enhancing reasoning quality. Extensive experiments on established EI benchmarks show that PTEI enhances the Emotional Understanding (EU) capabilities of various LLMs, with the strongest improvement observed in GPT models. Combining PTEI with Chain-of-Thought (CoT) reasoning yields an additional 4 percent increase in accuracy. These findings underscore PTEI's contribution toward advancing AI systems with more sophisticated social and psychological grounding.
A. Jafari, Praboda Rajapaksha, R. Farahbakhsh et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
