[论文解读] Can Large Language Models Resolve Semantic Discrepancy in Self-Destructive Subcultures? Evidence from Jirai Kei

Peng Wang, Xilin Tao+6 more|arXiv (Cornell University)|Jan 8, 2026

Mental Health via Writing被引用 0

一句话总结

该论文提出 Subcultural Alignment Solver (SAS)，一个三部分框架（检索、对齐报告、文化对齐），通过提升大语言模型在侦测自我毁灭行为方面的能力，在“地侍 Kei”子文化中超越基线并与微调模型并驾齐驱。

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.

研究动机与目标

• Motivate the need to detect self-destructive behaviors within rapidly evolving subcultures like Jirai Kei.
• Identify limitations of current LLM approaches due to knowledge lag and semantic misalignment.
• Propose Subcultural Alignment Solver (SAS) to automatically retrieve, report, and align subcultural knowledge.
• Demonstrate SAS effectiveness against prompting methods and multi-agent baselines, including comparisons to fine-tuned LLMs.

提出的方法

• Subculture Retrieval: automatically search the web for information about a target subculture and return k results.
• Alignment Report Generation: synthesize retrieved results into a background report detailing terminology and context.
• Culture Alignment Solver: perform subculture alignment to interpret input content and produce final labels via a task solver.

实验结果

研究问题

• RQ1 Can current LLM-based methods understand fast-evolving subcultures and their nuanced expressions?
• RQ2 Does a retrieval-plus-alignment approach reduce semantic gaps between general language use and subcultural intent?
• RQ3 How does SAS compare to prompting, multi-agent, and fine-tuned baselines on Jirai Kei self-destructive behavior detection?

主要发现

• Prompting methods underperform on subculture-specific tasks.
• Agentic frameworks improve understanding, with Self-Refine showing consistent gains across LLMs.
• OWL’s autonomous tool-use does not achieve strongest performance in this subculture setting.
• SAS achieves state-of-the-art performance among tested models and can rival fine-tuned LLMs without additional fine-tuning.
• Retrieval-language choice affects performance, with English retrieval generally yielding richer results, while reporting language benefits from cultural adaptation.
• SAS generalizes to other subcultures (Menhera, Yami Kawaii, Tenshi Kaiwai) per expert scoring of generated reports.