LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community Feedback

arXiv:2605.30273 · cs.HC, cs.AI, cs.CL, cs.CY, cs.SI · Submitted 2026-05-28 · Read on arXiv

cs.HC, cs.AI, cs.CL, cs.CY, cs.SI

Submitted: 2026-05-28

Updated: 2026-09-05

Comments: EMNLP 2026 (Main)

Journal ref: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Main Conference

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 19× in this paper · explained in 1 episode
• Online Community — 13× in this paper
• Improvement Model — 12× in this paper
• Actionability — 11× in this paper · explained in 3 episodes
• Semantic Similarity — 9× in this paper · explained in 2 episodes
• Generation Model — 7× in this paper
• Direct Preference Optimization — 6× in this paper
• Adam — 5× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Personalization — 4× in this paper · explained in 2 episodes
• Direct Preference Optimization (DPO) — 3× in this paper · explained in 9 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Words Per Response — 3× in this paper
• Words Per Sentence — 3× in this paper
• Accountability — 2× in this paper · explained in 2 episodes
• AdamW Optimizer — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Emotional Resonance — 2× in this paper · explained in 2 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Semantic Alignment — 2× in this paper · explained in 3 episodes
• Supervised Fine Tuning — 2× in this paper
• Actor — 1× in this paper · explained in 3 episodes
• Alignment Methods — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Categorical Dynamic Index — 1× in this paper
• Generalizability — 1× in this paper · explained in 6 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vector Representations — 1× in this paper · explained in 2 episodes

Sources

• Modeling Empathy and Distress in Reaction to News Stories
• PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support
• CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking
• Psy-LLM: Scaling up Global Mental Health Psychological Services with AI-based Large Language Models
• CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Mapping Caregiver Needs to AI Chatbot Design: Strengths and Gaps in Mental Health Support for Alzheimer's and Dementia Caregivers
• Interpersonal Theory of Suicide as a Lens to Examine Suicidal Ideation in Online Spaces

Related papers

• EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning
• EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
• HAGI++: Head-Assisted Gaze Imputation and Generation
• Linking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving
• Review of Explainable Decision Support and Adaptive Human-Machine Interfaces for Automation Transparency in Maritime Autonomous Surface Ships
• Towards Cognitive Process-Aware Proactive Writing Support