Papers by Seonglae Cho
LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries (2025.acl-srw)
Copied to clipboard
Zekun Wu, Seonglae Cho, Umar Mohammed, Cristian Enrique Munoz Villalobos, Kleyton Da Costa, Xin Guan, Theo King, Ze Wang, Emre Kazim, Adriano Koshiyama
| Challenge: | Open-source AI libraries present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity, and regulatory compliance. |
| Approach: | They propose a system that leverages large language models and agentic workflows to perform deep, evidence-based evaluations of open-source AI libraries. |
| Outcome: | The proposed system covers up to 88% of OpenSSF Scorecard checks and uncovers 19 additional risks per library. |
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Datasets Dependency (2025.acl-srw)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. |
| Approach: | They propose a method that trains SAEs on the model’s own synthetic dataset and a model-specific model to capture model-internal features. |
| Outcome: | The proposed method outperforms SAEs trained on web-based datasets and exhibits lower Fake Feature Ratio in 5 out of 7 models. |
RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization (2024.naacl-demo)
Copied to clipboard
| Challenge: | Abstractive summarization has emerged as a critical tool in the era of information overload. |
| Approach: | They propose an unsupervised summarization framework that utilizes relation triples as the basic unit for summarizing. |
| Outcome: | The proposed framework visualizes salience levels for sentences, relation triples, and phrases. |