Abstract--General-purpose large language models (LLMs) have demonstrated remarkable generative and reasoning capabilities but remain limited in healthcare and caregiving applications due to two key deficiencies: factual unreliability and a lack of empathetic communication. These shortcomings pose significant risks in sensitive contexts where users, particularly nonprofessionals and caregivers, seek medically relevant guidance or emotional reassurance. T o address these challenges, we introduce a Direct Preference Optimization (DPO)-based alignment framework designed to improve factual correctness, semantic coherence, and human-centric qualities such as empathy, politeness, and simplicity in caregiver-patient dialogues. Our approach fine-tunes domain-adapted Large Language Models (LLMs) using pairwise preference data, where preferred responses reflect supportive and accessible communication styles while rejected ones represent prescriptive or overly technical tones. Empirical evaluations across multiple open and proprietary LLMs show that our DPO-tuned models achieve higher semantic alignment, improved factual accuracy, and stronger human-centric evaluation scores compared to baseline and commercial alternatives such as Google's medical dialogue systems. These improvements demonstrate that preference-based alignment offers a scalable and transparent pathway toward developing trustworthy, empathetic, and clinically informed AI assistants for caregiver and healthcare communication. Caring for individuals with chronic or neuro-degenerative conditions such as Alzheimer's disease and dementia requires not only clinical coordination but also constant emotional resilience. Family caregivers and care partners often become the primary interpreters of medical information, navigating complex treatment decisions, behavioral changes, and communication challenges on a daily basis. LLMs have rapidly become integrated into everyday life. They can explain complex ideas in plain language, adjust to a user's tone, and offer a sense of understanding that static websites cannot. For caregivers seeking clear, kind, and quick answers, these systems can feel like an always-available companion in moments of doubt or stress.

Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can amplify risk. We propose ProSocialAlign, a test-time, parameter-efficient framework that steers generation toward safe, empathetic, and value-aligned responses without retraining the base model. We formalize five human-centered objectives and cast safety as lexicographic constrained generation: first, applying hard constraints to eliminate harmful continuations; then optimizing for prosocial quality within the safe set. Our method combines (i) directional regulation, a harm-mitigation mechanism that subtracts a learned "harm vector" in parameter space, and (ii) preference-aware autoregressive reward modeling trained jointly across attributes with gradient conflict resolution, enabling fine-grained, user-controllable decoding. Empirical evaluations across five safety benchmarks demonstrate state-of-the-art performance, reducing unsafe leakage and boosting alignment to human values, with strong gains across multiple evaluation metrics. ProSocialAlign offers a robust and modular foundation for generating context-sensitive, safe, and human-aligned responses at inference time.

As web platforms evolve towards greater personalization and emotional complexity, conversational agents must transcend superficial empathy to demonstrate identity-aware emotional reasoning. However, existing systems face two limitations: (1) reliance on situation-centric datasets lacking persistent user identity, which hampers the capture of personalized affective nuances; and (2) dependence on opaque, coarse reward signals that hinder development of verifiable empathetic reasoning. To address these gaps, we introduce KardiaBench, a large-scale user-grounded benchmark comprising 178,080 QA pairs across 22,080 multi-turn conversations anchored to 671 real-world profiles. The dataset is constructed via a model-in-the-loop pipeline with iterative rubric-guided refinement to ensure psychological plausibility and persona consistency. This progressive empathy pipeline that integrates user comprehension, contextual reasoning, and emotion perception into conversations, followed by iterative critique and rubric-based refinement to ensure psychological plausibility, emotional fidelity, and persona consistency. Building on this, we propose Kardia-R1, a framework that trains models for interpretable, stepwise empathetic cognition. Kardia-R1 leverages Rubric-as-Judge Empathetic Reinforcement Learning (Rubric-ERL), a GRPO-based method that uses explainable, human-aligned rubric rewards to tightly couple user understanding, emotional inference, and supportive response generation. Extensive experiments across four LLM backbones demonstrate that Kardia-R1 consistently outperforms othet methods in emotion accuracy, empathy, relevance, persona consistency, and safety. Our dataset and model will be released at https://github.com/JhCircle/Kardia-R1.

Recent advances enable Large Language Models (LLMs) to generate AI personas, yet their lack of deep contextual, cultural, and emotional understanding poses a significant limitation. This study quantitatively compared human responses with those of eight LLM-generated social personas (e.g., Male, Female, Muslim, Political Supporter) within a low-resource environment like Bangladesh, using culturally specific questions. Results show human responses significantly outperform all LLMs in answering questions, and across all matrices of persona perception, with particularly large gaps in empathy and credibility. Furthermore, LLM-generated content exhibited a systematic bias along the lines of the ``Pollyanna Principle'', scoring measurably higher in positive sentiment ($Φ_{avg} = 5.99$ for LLMs vs. $5.60$ for Humans). These findings suggest that LLM personas do not accurately reflect the authentic experience of real people in resource-scarce environments. It is essential to validate LLM personas against real-world human data to ensure their alignment and reliability before deploying them in social science research.

Abstract--Prevalent empathy prediction techniques primarily concentrate on a singular modality, typically textual, thus neglecting multi-modal processing capabilities. They also overlook the utilization of certain privileged information, which may encompass additional empathetic content. In response, we introduce an advanced multi-modal empathy prediction method integrating video, audio, and text information. The method comprises the Multi-Modal Empathy Prediction and Supervisory Documentation Assisted Training. We use pre-trained networks in the empathy prediction network to extract features from various modalities, followed by a cross-modal fusion. This process yields a multi-modal feature representation, which is employed to predict empathy labels. T o enhance the extraction of text features, we incorporate supervisory documents as privileged information during the assisted training phase. Specifically, we apply the Latent Dirichlet Allocation model to identify potential topic distributions to constrain text features. These supervisory documents, created by supervisors, focus on the counseling topics and the counselor's display of empathy. Notably, this privileged information is only available during training and is not accessible during the prediction phase. Experimental results on the multi-modal and dialogue empathy datasets demonstrate that our approach is superior to the existing methods. MP A THY is characterized by an emotional response that arises from the interplay between inherent traits and situational factors. This empathetic response is spontaneously triggered, yet it is also sculpted by deliberate cognitive control.

Large Language Model (LLM)-based conversational agents offer promising solutions for mental health support, but lack cultural responsiveness for diverse populations. This study evaluated the effectiveness of cultural prompting in improving cultural responsiveness and perceived empathy of LLM-generated therapeutic responses for Chinese American family caregivers. Using a randomized controlled experiment, we compared GPT-4o and Deepseek-V3 responses with and without cultural prompting. Thirty-six participants evaluated input-response pairs on cultural responsiveness (competence and relevance) and perceived empathy. Results showed that cultural prompting significantly enhanced GPT-4o's performance across all dimensions, with GPT-4o with cultural prompting being the most preferred, while improvements in DeepSeek-V3 responses were not significant. Mediation analysis revealed that cultural prompting improved empathy through improving cultural responsiveness. This study demonstrated that prompt-based techniques can effectively enhance the cultural responsiveness of LLM-generated therapeutic responses, highlighting the importance of cultural responsiveness in delivering empathetic AI-based therapeutic interventions to culturally and linguistically diverse populations.

The LLM field has spent a year perfecting RL for tasks machines already excel at, math, code, and deterministic reasoning, while completely sidestepping the domain that actually defines human intelligence: subjective, emotionally grounded, personality sensitive conversation. This space has often been regarded as inherently subjective and challenging to formalize, making it appear unsuitable for conventional RL pipelines. We show that it is not only possible and it is a solvable and transformative RL problem. We propose the first framework that infers user personality on the fly and optimizes model behavior toward personalized conversational preferences. Contrary to the widespread belief that RL collapses in non-verifiable settings, our method produces consistent, robust, and dramatic improvements in humanlike interaction quality. We also introduce the first dynamic emotional intelligence evaluation suite to quantify these gains. Our model, which is introduced as Echo-N1, behaves far above its base version and outperforming the proprietary Doubao 1.5 Character. This work establishes a new frontier for RL: optimizing models for the deeply subjective, deeply human dimensions of conversation.

Abstract--Noisy self-reported empathy scores challenge supervised learning for empathy regression. While many algorithms have been proposed for learning with noisy labels in textual classification problems, the regression counterpart is relatively under-explored. We propose UPLME, an uncertainty-aware probabilistic language modelling framework to capture label noise in empathy regression tasks. One of the novelties in UPLME is a probabilistic language model that predicts both empathy scores and heteroscedastic uncertainty, and is trained using Bayesian concepts with variational model ensembling. We further introduce two novel loss components: one penalises degenerate Uncertainty Quantification (UQ), and another enforces similarity between the input pairs on which empathy is being predicted. UPLME achieves state-of-the-art performance (Pearson Correlation Coefficient: 0.558 0.580 and 0.629 0.634) in terms of the performance reported in the literature on two public benchmarks with label noise. Through synthetic label noise injection, we demonstrate that UPLME is effective in distinguishing between noisy and clean samples based on the predicted uncertainty. UPLME further outperform (Calibration error: 0.571 0.376) a recent variational model ensembling-based UQ method designed for regression problems.

This report presents the Empathetic Cascading Networks (ECN) framework, a multi-stage prompting method designed to enhance the empathetic and inclusive capabilities of large language models. ECN employs four stages: Perspective Adoption, Emotional Resonance, Reflective Understanding, and Integrative Synthesis, to guide models toward generating emotionally resonant and contextually aware responses. Experimental results demonstrate that ECN achieves the highest Empathy Quotient (EQ) scores across GPT-3.5-turbo and GPT-4, while maintaining competitive Regard and Perplexity metrics. These findings emphasize ECN's potential for applications requiring empathy and inclusivity in conversational AI.

We investigate empathy-in-action -- the willingness to sacrifice task efficiency to address human needs -- as a linear direction in LLM activation space. Using contrastive prompts grounded in the Empathy-in-Action (EIA) benchmark, we test detection and steering across Phi-3-mini-4k (3.8B), Qwen2.5-7B (safety-trained), and Dolphin-Llama-3.1-8B (uncensored). Detection: All models show AUROC 0.996-1.00 at optimal layers. Uncensored Dolphin matches safety-trained models, demonstrating empathy encoding emerges independent of safety training. Phi-3 probes correlate strongly with EIA behavioral scores (r=0.71, p<0.01). Cross-model probe agreement is limited (Qwen: r=-0.06, Dolphin: r=0.18), revealing architecture-specific implementations despite convergent detection. Steering: Qwen achieves 65.3% success with bidirectional control and coherence at extreme interventions. Phi-3 shows 61.7% success with similar coherence. Dolphin exhibits asymmetric steerability: 94.4% success for pro-empathy steering but catastrophic breakdown for anti-empathy (empty outputs, code artifacts). Implications: The detection-steering gap varies by model. Qwen and Phi-3 maintain bidirectional coherence; Dolphin shows robustness only for empathy enhancement. Safety training may affect steering robustness rather than preventing manipulation, though validation across more models is needed.