Papers by Sungwon Park
Platform-Invariant Topic Modeling via Contrastive Learning to Mitigate Platform-Induced Bias (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing topic models that analyze documents from multiple platforms are not able to capture the authentic topics due to platform-induced biases. |
| Approach: | They propose to use a platform-invariant contrastive learning algorithm to reduce platform influence in topic models by removing platform-specific jargon word sets. |
| Outcome: | The proposed model reduces platform influence in topic models by developing a platform-invariant contrastive learning algorithm and removing platform-specific jargon word sets. |
SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger (2026.acl-long)
Copied to clipboard
| Challenge: | open-weight large language models increase vulnerability to malicious fine-tuning . despite these advantages, open-source LLMs increase the potential for misuse . |
| Approach: | They propose a safety guide for open-weight large language models that guides fine-tuning toward the safety manifold to preserve alignment. |
| Outcome: | The proposed safety guidance trigger significantly improves robustness against malicious fine-tuning. |
Unified Neural Topic Model via Contrastive Learning and Term Weighting (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent techniques employ pretrained language models to improve topic quality. |
| Approach: | They propose a topic-based model that uses contrastive learning and term weighting to learn from a pretrained language model and discover influential terms from semantically coherent clusters. |
| Outcome: | The proposed model outperforms baselines across multiple topic coherence measures and can be used as an add-on to existing topic models and improves their performance. |