用大模型分析枪支暴力幸存者访谈，发现效果有限且易丢失关键信息。
Can LLMs Understand the Impact of Trauma? Costs and Benefits of LLMs Coding the Interviews of Firearm Violence Survivors
- 用开源大模型对21名黑人男性幸存者访谈进行自动编码
- 模型识别重要主题能力弱，相关性普遍偏低，依赖数据处理方式
- 安全机制导致大量叙事内容被删减，伦理风险突出
枪支暴力是紧迫的公共健康问题，但针对幸存者亲身经历的研究仍缺乏资金支持且难以规模化。深度访谈等定性研究有助于理解社区枪支暴力的个人与社会影响，并指导有效干预措施。然而，通过主题分析和归纳编码手动解析这些叙述耗时费力。近年来大语言模型（LLMs）的发展为自动化此过程提供了可能，但其能否准确、合乎伦理地捕捉弱势群体的经验仍存疑。本研究评估了开源LLMs在对21名黑人男性枪支暴力幸存者访谈进行归纳编码中的应用。结果表明，尽管部分模型配置能识别出重要主题，但整体相关性较低，且高度依赖数据预处理。此外，LLM的安全防护机制导致大量叙事内容被删除。这些发现凸显了大模型辅助定性编码的潜力与局限，也强调了在涉及边缘化群体的研究中应用AI所面临的伦理挑战。
原文摘要 · Abstract (English)
Firearm violence is a pressing public health issue, yet research into survivors' lived experiences remains underfunded and difficult to scale. Qualitative research, including in-depth interviews, is a valuable tool for understanding the personal and societal consequences of community firearm violence and designing effective interventions. However, manually analyzing these narratives through thematic analysis and inductive coding is time-consuming and labor-intensive. Recent advancements in large language models (LLMs) have opened the door to automating this process, though concerns remain about whether these models can accurately and ethically capture the experiences of vulnerable populations. In this study, we assess the use of open-source LLMs to inductively code interviews with 21 Black men who have survived community firearm violence. Our results demonstrate that while some configurations of LLMs can identify important codes, overall relevance remains low and is highly sensitive to data processing. Furthermore, LLM guardrails lead to substantial narrative erasure. These findings highlight both the potential and limitations of LLM-assisted qualitative coding and underscore the ethical challenges of applying AI in research involving marginalized communities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。