# First, Do No Harm: AI Supervisor Scaffolds Novice Growth in Counselor Education

arXiv: https://arxiv.org/abs/2508.09042 · HTML: https://mlsanity.com/paper/2508.09042/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support](https://mlsanity.com/paper/2009.08441/) (2020)
- [Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory](https://mlsanity.com/paper/2407.03103/) (2024)
- [Rehearsal: Simulating Conflict to Teach Conflict Resolution](https://mlsanity.com/paper/2309.12309/) (2023)
- [HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapy](https://mlsanity.com/paper/2403.05574/) (2024)
- [CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering](https://mlsanity.com/paper/2403.16008/) (2024)
- [Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions](https://mlsanity.com/paper/2408.15787/) (2024)
- [PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counseling](https://mlsanity.com/paper/2412.13660/) (2024)
- [PATIENT-Psi: Using Large Language Models to Simulate Patients for Training Mental Health Professionals](https://mlsanity.com/paper/2405.19660/) (2024)
- [COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas](https://mlsanity.com/paper/2205.00872/) (2022)
- [Multi-Level Feedback Generation with Large Language Models for Empowering Novice Peer Counselors](https://mlsanity.com/paper/2403.15482/) (2024)
- [Emotional Support with LLM-based Empathetic Dialogue Generation](https://mlsanity.com/paper/2507.12820/) (2025)

## Abstract (arXiv)

The most dangerous mistakes a novice counselor makes are not the obvious ones: they are utterances that sound caring while quietly violating professional ethics and leaving vulnerable clients less protected. We build an AI supervisor that does not replace novice counselors, but grows them-teaching them to internalize ethical violations they would otherwise never notice. What makes this supervisor non-trivial is not detection but teaching: it must locate the ethical-violating utterance, diagnose the ethical violation against APA principles, and deliver feedback that explains not just what went wrong, but why it is risky and how to respond differently. The core obstacle is that (1) ethical violations are by nature unlabeled in real clinical data, and (2) existing AI counselors trained only to match correct answers will never learn to teach. We resolve both at once: a controllable AI novice that intentionally enacts predefined mistake categories makes supervision labels a natural byproduct of generation, yielding ETHICSCAFF, a 9,915-instance human-in-the-loop dataset; and GRPO under a Novice Growth Reward (NGR) optimizes the supervisor not for answer correctness but for whether a weaker novice model actually improves after reading its explanation. Experiments show that a novice guided by our supervisor outperforms an unguided peer on clinical metrics, and that teaching-oriented optimization via NGR further sharpens the supervisor's own ethical detection. In a user study with novice counseling-psychology students, participants show significant self-efficacy gains across all eight assessed competencies after receiving AI supervisory feedback, demonstrating that the scaffold transfers from simulation to real-world practice.