# Can LLMs Understand the Impact of Trauma? Costs and Benefits of LLMs Coding the Interviews of Firearm Violence Survivors

arXiv: https://arxiv.org/abs/2604.16132 · HTML: https://mlsanity.com/paper/2604.16132/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 36 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis](https://mlsanity.com/paper/2310.15100/) (2023)
- [CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models](https://mlsanity.com/paper/2304.07366/) (2023)
- [Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs](https://mlsanity.com/paper/2502.01926/) (2025)
- [HICode: Hierarchical Inductive Coding with LLMs](https://mlsanity.com/paper/2509.17946/) (2025)
- [ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context](https://mlsanity.com/paper/2407.06866/) (2024)
- [QuaLLM: An LLM-based Framework to Extract Quantitative Insights from Online Forums](https://mlsanity.com/paper/2405.05345/) (2024)
- [RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews](https://mlsanity.com/paper/2402.02656/) (2024)
- [DeTAILS: Deep Thematic Analysis with Iterative LLM Support](https://mlsanity.com/paper/2510.17575/) (2025)
- [Nutrition Facts, Drug Facts, and Model Facts: Putting AI Ethics into Practice in Gun Violence Research](https://mlsanity.com/paper/2402.09286/) (2024)
- [Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants](https://mlsanity.com/paper/2508.18541/) (2025)

## Abstract (arXiv)

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.