3 papers
cs.CL2024
Efficient and Accurate Memorable Conversation Model using DPO based on sLLM
Youngkyung Seo, Yoonseok Heo, Jun-Seok Koh +1
In multi-session dialog system, it is essential to continuously update the memory as the session progresses. Simply accumulating memory can make it difficult to focus on the conten…
cs.CL2024
Enhancing Psychotherapy Counseling: A Data Augmentation Pipeline Leveraging Large Language Models for Counseling Conversations
Jun-Woo Kim, Ji-Eun Han, Jun-Seok Koh +2
We introduce a pipeline that leverages Large Language Models (LLMs) to transform single-turn psychotherapy counseling sessions into multi-turn interactions. While AI-supported onli…
cs.CL2024
PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models
Ji-Eun Han, Jun-Seok Koh, Hyeon-Tae Seo +2
We present a novel end-to-end personality-based synthetic dialogue data generation pipeline, specifically designed to elicit responses from large language models via prompting. We…