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

TL;DR

This paper introduces SAS, a multi-agent framework that improves large language models' ability to detect self-destructive behaviors in subcultures by addressing knowledge lag and semantic misalignment.

Contribution

The paper presents SAS, a novel multi-agent approach that enhances LLM performance in subcultural self-destructive behavior detection through automatic retrieval and alignment techniques.

Findings

SAS outperforms the existing OWL framework.

SAS performs comparably to fine-tuned LLMs.

The framework effectively addresses knowledge lag and semantic misalignment.

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.