# Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness

arXiv: https://arxiv.org/abs/2609.26865 · HTML: https://mlsanity.com/paper/2609.26865/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 69 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant](https://mlsanity.com/paper/2405.01576/) (2024)
- [Investigating Affective Use and Emotional Well-being on ChatGPT](https://mlsanity.com/paper/2504.03888/) (2025)
- [How AI and Human Behaviors Shape Psychosocial Effects of Extended Chatbot Use: A Longitudinal Randomized Controlled Study](https://mlsanity.com/paper/2503.17473/) (2025)
- [ShareChat: A Dataset of Chatbot Conversations in the Wild](https://mlsanity.com/paper/2512.17843/) (2025)
- [Measuring and mitigating overreliance to build human-compatible AI](https://mlsanity.com/paper/2509.08010/) (2025)
- [YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models](https://mlsanity.com/paper/2509.08997/) (2025)
- [Individual-level interventions against sycophantic AI reduce its appeal but not its persuasiveness](https://mlsanity.com/paper/2607.25166/) (2026)

## Abstract (arXiv)

Conversational AI systems can pose safety risks to their users such as hallucination, sycophancy, overconfidence, and anthropomorphism, but these risks are difficult for users to detect during everyday use. We introduce Safety Nudges, a browser-based tool that provides lightweight, in situ flags when concerning behavior is detected in chatbot conversations. We evaluated Safety Nudges in a two-week field study with 45 frequent chatbot users, collecting interaction logs, surveys, and feedback on individual nudges. Participants found the tool useful, clear, and minimally disruptive, with nearly all users reporting an increased awareness of potential AI harms, though we found that this improved awareness alone did not necessarily lead to discernible behavioral changes. Our results suggest that user facing safety nudges can complement model-level safeguards by helping people critically evaluate AI responses in context, while highlighting the importance of relevance, calibration, and user control in nudge design for conversational AI safety. The code for our Safety Nudges extension is publicly available at https://github.com/jtbwedgwood/safety-nudges.