Papers by Palakorn Achananuparp
Consistent Client Simulation for Motivational Interviewing-based Counseling (2025.acl-long)
Copied to clipboard
Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Nicholas Gabriel Lim, Cameron Tan Shi Ern, Phey Ling Kit, Jenny Giam Xiuhui, John Pinto, Ee-Peng Lim
| Challenge: | Existing approaches to simulate human clients in mental health counseling are limited and cost prohibitive. |
| Approach: | They propose a framework that supports consistent client simulation for mental health counseling by tracking the mental state of a simulated client, controlling its state transitions, and generating for each state behaviors consistent with the client’s motivation, beliefs, preferred plan to change, and and receptivity. |
| Outcome: | The proposed framework can simulate human clients for mental health counseling tasks and achieve higher consistency than previous methods. |
MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reasoning large language models (LLMs) generate responses without explicitly aligning thoughts with counseling techniques, limiting their effectiveness. |
| Approach: | They propose a lightweight thinking model that generates therapeutic thoughts to guide MI counseling agents in strategy selection and response generation. |
| Outcome: | The proposed model achieves theory-of-mind assessment comparable to state-of the-art systems with an order of magnitude less computation. |
Speaker Verification in Agent-generated Conversations (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have increased the capabilities of conversational AI to solve challenging dialogue problems. |
| Approach: | They propose a task to verify whether two sets of utterances originate from the same speaker. |
| Outcome: | The proposed task aims to verify whether two sets of utterances originate from the same speaker. |
MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation frameworks assess isolated responses using coarse-grained taxonomies or static datasets. |
| Approach: | They propose a role-aware mental health safety taxonomy that characterizes clinically significant harm in terms of interactional roles an AI counselor adopts. |
| Outcome: | The proposed framework significantly improves failure-mode coverage and diagnostic granularity. |
CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration (2025.acl-long)
Copied to clipboard
Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Phey Ling Kit, Nicholas Gabriel Lim, Cameron Tan Shi Ern, Ee-Peng Lim
| Challenge: | Motivational Interviewing (MI) is a client-centered counseling technique designed to address ambivalence and facilitate behavior change in clients. |
| Approach: | They propose to use a STAR framework to evoke change talk by using large language models to assess MI skill competency, client’s state inference accuracy, topic exploration proficiency, and overall counseling success. |
| Outcome: | The proposed agent outperforms several state-of-the-art methods and shows more realistic counselor-like behavior. |