Jy-yong Sohn

Mini-Batch Optimization of Contrastive Loss

2023 · arXiv (Cornell University)

Contrastive learning has gained significant attention as a method for self-supervised learning. The contrastive loss function ensures that embeddings of positive sample pairs (e.g., different samples from the same class or different views of the …

Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses

2024 · arXiv (Cornell University)

Mitigating hallucination issues is a key challenge that must be overcome to reliably deploy large language models (LLMs) in real-world scenarios. Recently, various methods have been proposed to detect and revise factual errors in LLM-generated …

Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective

2025 · arXiv (Cornell University)

In continual learning scenarios, catastrophic forgetting of previously learned tasks is a critical issue, making it essential to effectively measure such forgetting. Recently, there has been growing interest in focusing on representation forgetting, the forgetting …