The paper presents an LLM-based framework for automatically classifying crisis levels in psychological support hotlines, addressing variability in human judgments and staffing constraints. It introduces a paralinguistic injection method that embeds non‑verbal emotional cues into transcripts, allowing the model to consider acoustic nuances. A reasoning‑enhanced training strategy encourages the model to produce diagnostic reasoning chains, which regularizes and improves classification, achieving a macro F1‑score of 0.802 and accuracy of 0.805 in 5‑fold cross‑validation.
By Terumi Chiba, Yang Luo, Ziyun Cui, Yongsheng Tong, Chao Zhang
arXiv:2512. 06227v3 Announce Type: replace-cross Abstract: Real-world indicators play an important role in many Natural Language Processing (NLP) applications, such as life events for mental health analysis and risky behaviours for online safety, yet labelling such information is often costly and/or difficult due to its multi-label and dynamic nature.
By Junyu Mao, Anthony Hills, Talia Tseriotou, Maria Liakata, Aya Shamir, Dan Sayda, Dana Atzil-Slonim, Natalie Djohari, Pamela Ugwudike, Mahesan Niranjan, Stuart E. Middleton
arXiv:2607. 22692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk.
By Anabela C. Areias, Catarina Botelho, Ant\'onio Farinhas, Areti Vassilopoulos, Dora Janela, Xin Tong, Nuno M. Guerreiro, Maya D'Eon, Fab\'iola Costa, Ricardo Rei
arXiv:2608. 11200v1 Announce Type: cross Abstract: Synthetic dialogue generation offers a way to study conversational dynamics in sensitive domains where real data are difficult to access, release, or annotate.
By Chen Lyu, Xingwei Tan, Simon Cullen, Shelley Wilson, Lois Arthurs, Arshad Jhumka, Gabriele Pergola
Synthetic dialogue generation offers a way to study conversational dynamics in sensitive domains where real data are difficult to access, release, or annotate. The underlying abuse may occur online or offline: threats and coercion can appear directly in messages, while behaviours such as surveillance, isolation, stalking, and physical violence may be planned, disclosed, or referred to conversationally.
arXiv:2607. 19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compose into harm.
By Sanjay Mishra, Divya Chukkapalli, Ganesh R. Naik
arXiv:2609.15855v1 Announce Type: cross
Abstract: % !TEX root = ../main.tex People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk con...
By Laura M. Vowels, Matthew J. Vowels, Shivali Sharma, Apoorv Jha, Rehnuma Choudhury, Wasseem El Sarraj, Rachel Francois-Walcott, Aruba Hussain, Sarah Ingram, Angela Loulopoulou, Adva Segal, Elena Volkova
arXiv:2601.09717v2 Announce Type: replace-cross
Abstract: Online medical consultations contain sensitive health information whose privacy implications depend not only on the entities mentioned but al...
By Yiwei Yan, Guanfeng Liu
arXiv:2606. 03812v1 Announce Type: new Abstract: Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identification.
By Sanjay Das, Ran Elgedawy, Ethan Seefried, Ryan Burchfield, Tirthankar Ghosal
The paper introduces EMPATH, a framework that analyzes emotion dynamics in crisis counseling dialogues at three levels: turn-level labels, transition probabilities, and global conversation archetypes. Using EMPATH on text-based conversations between Black texters and volunteers about grief, the study reveals persistent negative affect, gradual shifts toward hope, distinct emotional roles for texters and volunteers, and varied recovery paths. These findings demonstrate how dynamic emotion analysis can uncover informative patterns in crisis support interactions.
By Ziwei Gong, Yuchen Huang, Wen Liang, Nicholas Deas, Melanie Subbiah, Kathleen McKeown, Julia Hirschberg
The paper reviews how large language models are applied in mental health, covering areas such as social media analysis, clinical conversational agents, therapy support tools, prompt engineering, and multimodal learning. It synthesizes interdisciplinary studies that use social media posts, electronic medical records, and multimodal inputs to detect depression, assess suicide risk, provide personalized therapy, and generate psychoeducational content. The review also discusses advances in model interpretability, annotation strategies, multimodal fusion techniques, and highlights ethical, sociotechnical, and regulatory challenges while proposing frameworks for safe, equitable, and accountable deployment.
By Yisong Chen, Yifan Gao, Sijing Yu, Chuqing Zhao, Yang Lu
The paper introduces a method to predict whether volunteer mental‑health crisis counselors will improve their conversational skills early in their careers. It focuses on identifying moments counselors initially struggle with, tracking how they adapt to similar moments in later conversations, and using these early adaptations to forecast long‑term improvement. The approach outperforms baseline models that rely solely on conversation transcripts.
By Vivian Nguyen, Lillian Lee, Elizabeth A. Olson, Cristian Danescu-Niculescu-Mizil