# Can Large Language Models Resolve Semantic Discrepancy in Self-Destructive Subcultures? Evidence from Jirai Kei Source: [Can Large Language Models Resolve Semantic Discrepancy in Self-Destructive Subcultures? Evidence from Jirai Kei]() Collection index: [llms.txt]() Data updated: 2026-05-27T05:00:05.520Z Authors: Peng Wang, Xilin Tao, Siyi Yao, Jiageng Wu, Yuntao Zou, Zhuotao Tian, Libo Qin, Dagang Li Published: 2026-01-08T15:02:41.000Z ## Abstract Self-destructive behaviors are linked to complex psychological states and can be challenging to diagnose. These behaviors may be even harder to identify within subcultural groups due to their unique expressions. As large language models (LLMs) being deployed across various fields, some researchers have begun exploring their application for detecting self-destructive behaviors. Motivated by this, we investigate self-destructive behavior detection within subcultures using current LLM-based methods. However, these methods have two main challenges: (1) Knowledge Lag: Subcultural slang evolves rapidly, faster than LLMs' training cycles; and (2) Semantic Misalignment: it is challenging to grasp the specific and nuanced expressions unique to subcultures. To address these issues, we propose Subcultural Alignment Solver (SAS), a multi-agent framework that incorporates automatic retrieval and subculture alignment, significantly boosting the performance of LLMs in detecting self-destructive behavior. Our experimental results show that SAS outperforms the current advanced multi-agent framework OWL. Notably, it competes well with fine-tuned LLMs. We hope that SAS will advance the field of self-destructive behavior detection in subcultural contexts and serve as a valuable resource for future researchers. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Eating Disorder Detection on JiraiBench 1.0 (test)](): Eating Disorder Detection; JiraiBench 1.0 (test); Macro F1: 79.99. - [Self-Harm Detection on JiraiBench 1.0 (test)](): Self-Harm Detection; JiraiBench 1.0 (test); Macro F1: 66.63. - [Overdose Detection on JiraiBench 1.0 (test)](): Overdose Detection; JiraiBench 1.0 (test); Macro F1: 0.7505. ## Original sources and implementation [Original paper]() [PDF]()