← Search

Hyeon-Tae Seo

2 accepted papers

2024

PSYDIAL: Personality-based Synthetic Dialogue Generation Using Large Language Models

COLING 2024main

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 design the prompts to generate more human-like dialogues considering real-world scenarios when users engage with chatbot…

2024

SuperST: Superficial Self-Training for Few-Shot Text Classification

COLING 2024main

In few-shot text classification, self-training is a popular tool in semi-supervised learning (SSL). It relies on pseudo-labels to expand data, which has demonstrated success. However, these pseudo-labels contain potential noise and provoke a risk of underfitting the decision boundary. While the pseu…