Can Large Language Models Resolve Semantic Discrepancy in Self-Destructive Subcultures? Evidence from Jirai Kei

2026-01-08

arXiv.org

AI Summary

This work addresses the challenge of detecting self-destructive behaviors within subcultural communities, which often evade recognition due to their unique expressive forms. Current large language models struggle with such tasks owing to knowledge obsolescence and semantic misalignment. To bridge this gap, we propose the Subcultural Alignment Solver (SAS), a novel multi-agent framework that integrates automated retrieval augmentation with a subcultural semantic alignment mechanism. SAS is the first to incorporate subcultural alignment into multi-agent systems, effectively mitigating semantic drift and knowledge lag in rapidly evolving contextual environments. Experimental results demonstrate that SAS significantly outperforms state-of-the-art multi-agent approaches such as OWL and achieves performance on the Jirai Kei subcultural dataset comparable to that of fine-tuned large language models, thereby validating its efficacy and innovation.

Technology Category

• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

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) are applied 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 proposed Subcultural Alignment Solver (SAS), a multi-agent framework that incorporates automatic retrieval and subculture alignment, significantly enhancing 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.

Problem

• Semantic Discrepancy
• Self-Destructive Subcultures
• Large Language Models
• Subcultural Slang
• Behavior Detection

Innovation

• Subcultural Alignment
• Large Language Models
• Self-Destructive Behavior Detection
• Multi-Agent Framework
• Semantic Misalignment