This paper introduces JiraiBench, the first bilingual benchmark for evaluating large language models' effectiveness in detecting self-destructive content across Chinese and Japanese social media communities. Focusing on the transnational "Jirai" (landmine) online subculture that encompasses multiple forms of self-destructive behaviors including drug overdose, eating disorders, and self-harm, we present a comprehensive evaluation framework incorporating both linguistic and cultural dimensions. Our dataset comprises 10,419 Chinese posts and 5,000 Japanese posts with multidimensional annotation along three behavioral categories, achieving substantial inter-annotator agreement. Experimental evaluations across four state-of-the-art models reveal significant performance variations based on instructional language, with Japanese prompts unexpectedly outperforming Chinese prompts when processing Chinese content. This emergent cross-cultural transfer suggests that cultural proximity can sometimes outweigh linguistic similarity in detection tasks. Cross-lingual transfer experiments with fine-tuned models further demonstrate the potential for knowledge transfer between these language systems without explicit target language training. These findings highlight the need for culturally-informed approaches to multilingual content moderation and provide empirical evidence for the importance of cultural context in developing more effective detection systems for vulnerable online communities.

A group of researchers from the Boston University School of Public Health and the VA Boston Healthcare System utilized machine learning to streamline the diagnosis tool for post-traumatic stress disorder (PTSD). According to their new study, released in the journal Assessment, some of the questions imposed in the Structural Clinical Interview for the Diagnostic Statistical Manual of Mental Disorders, Fifth Edition (SCID-5) could be eliminated, leading to more relevancy of the veteran population. "Our study is only a first step--but an important one, because it shows that machine learning methods can be used to help inform efforts to make care more efficient, without sacrificing or degrading the quality of care provided," said co-author Jaimie Graudus, in a news release. The new research included data from the SCID-5 assessments related to more than 1,200 military soldiers, half of which were male and the rest female, who served during the Afghanistan and Iraq conflicts. The use of random forests, a form of machine-learning system, was also incorporated into the study.