# Safe Generative Chats in a WhatsApp Intelligent Tutoring System

arXiv: https://arxiv.org/abs/2407.04915 · HTML: https://mlsanity.com/paper/2407.04915/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 7 of its 42 references that are in the map.
- First posted on arXiv 6 Jul 2024.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

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

- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias](https://mlsanity.com/paper/2404.00929/) (2024)
- [Red-Teaming for Generative AI: Silver Bullet or Security Theater?](https://mlsanity.com/paper/2401.15897/) (2024)
- [Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling](https://mlsanity.com/paper/2107.03451/) (2021)
- [Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference](https://mlsanity.com/paper/2310.03184/) (2023)
- [On the application of Large Language Models for language teaching and assessment technology](https://mlsanity.com/paper/2307.08393/) (2023)
- [Personalizing Content Moderation on Social Media: User Perspectives on Moderation Choices, Interface Design, and Labor](https://mlsanity.com/paper/2305.10374/) (2023)

## Abstract (arXiv)

Large language models (LLMs) are flexible, personalizable, and available, which makes their use within Intelligent Tutoring Systems (ITSs) appealing. However, that flexibility creates risks: inaccuracies, harmful content, and non-curricular material. Ethically deploying LLM-backed ITS systems requires designing safeguards that ensure positive experiences for students. We describe the design of a conversational system integrated into an ITS, and our experience evaluating its safety with red-teaming, an in-classroom usability test, and field deployment. We present empirical data from more than 8,000 student conversations with this system, finding that GPT-3.5 rarely generates inappropriate messages. Comparatively more common is inappropriate messages from students, which prompts us to reason about safeguarding as a content moderation and classroom management problem. The student interaction behaviors we observe provide implications for designers - to focus on student inputs as a content moderation problem - and implications for researchers - to focus on subtle forms of bad content.