Can LLM-Simulated Practice and Feedback Upskill Human Counselors? A Randomized Study with 90+ Novice Counselors
Ryan Louie, Raj Sanjay Shah, Ifdita Hasan Orney, Juan Pablo Pacheco, Emma Brunskill, Diyi Yang
Abstract
The growing demand for accessible mental health support requires training more counselors, yet existing approaches remain resourceintensive and difficult to scale. LLMs can realistically simulate patients and generate actionable feedback for training, but their actual impact on novice counselor skill development remains unknown. We developed an LLM-simulated practice and feedback system and conducted a randomized study with 94 novice counselors, comparing practice alone versus practice with feedback. We evaluated behavioral performance, self-efficacy, and qualitative reflections. Results showed the practice-and-feedback group improved in client-centered microskills (reflections, questions), while the practice-alone group showed no improvements. For empathy, the practice-alone group declined over time and performed significantly worse than the feedback group. Qualitative interviews reinforced these findings: feedback helped participants adopt a client-centered listening approach, while practice-alone participants remained solution-oriented. These results suggest LLM-based training systems can promote effective skill development, and combining simulated practice with structured feedback is critical for meaningful improvement.
• Human-centered computing → Empirical studies in HCI; Interactive systems and tools; Natural language interfaces; • Computing methodologies → Natural language processing.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers2
- OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior SimulationZiyi Wang, Yuxuan Lu, Wenbo Li, Amirali Amini et al.ACL 2026 · 26 citations
- "Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported InteractionsKellie Yu Hui Sim, Roy Ka-Wei Lee, Kenny Tsu Wei ChooCSCW 2026
Builds on27
- To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-makingZana Buçinca, Maja Barbara Malaya, Krzysztof Z. GajosCSCW 2021 · 962 citations
- Why Johnny Can't Prompt: How Non-AI Experts Try (and Fail) to Design LLM PromptsJ. D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, Qian YangCHI 2023 · 892 citations
- CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator NeedsMajeed Kazemitabaar, Runlong Ye, Xiaoning Wang, Austin Zachary Henley et al.CHI 2024 · 246 citations
- Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning ApproachAshish Sharma, Inna W. Lin, Adam S. Miner, David C. Atkins et al.WWW 2021 · 183 citations
- A Design Space for Intelligent and Interactive Writing AssistantsMina Lee, Katy Ilonka Gero, John Joon Young Chung, Simon Buckingham Shum et al.CHI 2024 · 133 citations
Related papers
- Scaffolding Empathy: Training Counselors with Simulated Patients and Utterance-level Performance VisualizationsIan Steenstra, Farnaz Nouraei, Timothy W. BickmoreCHI 2025 · 30 citations
- Multi-Level Feedback Generation with Large Language Models for Empowering Novice Peer CounselorsAlicja Chaszczewicz, Raj Sanjay Shah, Ryan Louie, Bruce A. Arnow et al.ACL 2024 · 12 citations
- PATIENT-ψ: Using Large Language Models to Simulate Patients for Training Mental Health ProfessionalsRuiyi Wang, Stephanie Milani, Jamie C. Chiu, Jiayin Zhi et al.EMNLP 2024 · 31 citations
- PAIR: Prompt-Aware margIn Ranking for Counselor Reflection Scoring in Motivational InterviewingDo June Min, Verónica Pérez-Rosas, Kenneth Resnicow, Rada MihalceaEMNLP 2022 · 10 citations
- Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to PrinciplesRyan Louie, Ananjan Nandi, William Fang, Cheng Chang et al.EMNLP 2024 · 37 citations
