Abstract
Understanding how large language models (LLMs) process emotionally sensitive content is critical for building safe and reliable systems, particularly in mental health contexts. We investigate the scaling behavior of LLMs on two key tasks: trinary classification of emotional safety (safe vs. unsafe vs. borderline) and multi-label classification using a six-category safety risk taxonomy. To support this, we construct a novel dataset by merging several human-authored mental health datasets (> 15K samples) and augmenting them with emotion re-interpretation prompts generated via ChatGPT. We evaluate four LLaMA models (1B, 3B, 8B, 70B) across zero-shot, few-shot, and fine-tuning settings. Our results show that larger LLMs achieve stronger average performance, particularly in nuanced multi-label classification and in zero-shot settings. However, lightweight fine-tuning allowed the 1B model to achieve performance comparable to larger models and BERT in several high-data categories, while requiring <2GB VRAM at inference. These findings suggest that smaller, on-device models can serve as viable, privacy-preserving alternatives for sensitive applications, offering the ability to interpret emotional context and maintain safe conversational boundaries. This work highlights key implications for therapeutic LLM applications and the scalable alignment of safety-critical systems.
Abstract (translated)
理解大型语言模型（LLM）处理情感敏感内容的方式对于构建安全可靠的系统至关重要，尤其是在心理健康领域。我们研究了两种关键任务中LLM的扩展行为：情感安全性的三分类（安全 vs 不安全 vs 边缘化）和使用六类风险分类体系进行多标签分类。为了支持这项工作，我们通过合并几个由人类编写的心理健康数据集（> 15,000个样本）并利用ChatGPT生成情感重新解释提示来构建了一个新颖的数据集。我们在零样本、少量样本和微调设置下评估了四个LLaMA模型（1B、3B、8B、70B）。我们的结果显示，较大的LLM在复杂的多标签分类以及零样本场景中表现出更强的平均性能。然而，在轻量级微调的情况下，1B模型在多个高数据类别中的表现可以与较大模型和BERT相媲美，并且仅需不到2GB的VRAM进行推理。这些发现表明，较小、便携式的模型可以在敏感应用中作为可行的选择，能够解释情感背景并维持安全对话界限。这项工作强调了治疗性LLM应用程序以及关键安全性系统可扩展对齐的关键影响。
URL
https://arxiv.org/abs/2509.04512
