# Large Language Models for Automatic Detection of Sensitive Topics

arXiv: https://arxiv.org/abs/2409.00940 · HTML: https://mlsanity.com/paper/2409.00940/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 58 references that are in the map.
- First posted on arXiv 2 Sep 2024.

## Builds on (most cited first, 7 of 7)

- [Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs](https://mlsanity.com/paper/2308.13387/) (2023)
- [Exploring the Limits of Language Modeling](https://mlsanity.com/paper/1602.02410/) (2016)
- [Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations](https://mlsanity.com/paper/2308.11995/) (2023)
- [Understanding the Benefits and Challenges of Using Large Language Model-based Conversational Agents for Mental Well-being Support](https://mlsanity.com/paper/2307.15810/) (2023)
- [If in a Crowdsourced Data Annotation Pipeline, a GPT-4](https://mlsanity.com/paper/2402.16795/) (2024)
- [Can Large Language Models Understand Context?](https://mlsanity.com/paper/2402.00858/) (2024)
- [Triaging Content Severity in Online Mental Health Forums](https://mlsanity.com/paper/1702.06875/) (2017)

## Built on by (most cited first, 3 of 3)

- [CoPE: A Small Language Model for Steerable and Scalable Content Labeling](https://mlsanity.com/paper/2512.18027/) (2025)
- [Probing Association Biases in LLM Moderation Over-Sensitivity](https://mlsanity.com/paper/2505.23914/) (2025)
- [Investigating AI in Peer Support via Multi-Module System-Driven Embodied Conversational Agents](https://mlsanity.com/paper/2511.22269/) (2025)

## Abstract (arXiv)

Sensitive information detection is crucial in content moderation to maintain safe online communities. Assisting in this traditionally manual process could relieve human moderators from overwhelming and tedious tasks, allowing them to focus solely on flagged content that may pose potential risks. Rapidly advancing large language models (LLMs) are known for their capability to understand and process natural language and so present a potential solution to support this process. This study explores the capabilities of five LLMs for detecting sensitive messages in the mental well-being domain within two online datasets and assesses their performance in terms of accuracy, precision, recall, F1 scores, and consistency. Our findings indicate that LLMs have the potential to be integrated into the moderation workflow as a convenient and precise detection tool. The best-performing model, GPT-4o, achieved an average accuracy of 99.5% and an F1-score of 0.99. We discuss the advantages and potential challenges of using LLMs in the moderation workflow and suggest that future research should address the ethical considerations of utilising this technology.