Publications

Pre-print (arXiv)

[P1] HyperCLOVA X Technical Report [paper]

[P2] Language Models Show Stable Value Orientations Across Diverse Role-Plays  [paper]

[P3] Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection [paper]

International Conferences

[C11] Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts  [paper]

[C10] Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model [paper]

[C9] Instruction Tuning with Human Curriculum [paper]

[C8] Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP [paper]

[C7] Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learning [paper]

[C6] CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels [paper]

[C5] Prompt-Augmented Linear Probing: Scaling Beyond The Limit of Few-shot In-Context Learners [paper]

[C4] Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations [paper]

[C3] Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble [paper]

[C2] Masked Contrastive Learning for Anomaly Detection [paper]

[C1] Automatic Generation of Multiple-Choice Fill-in-the-blank Question Using Document Embedding [paper]

International Workshops

[W3] Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator [paper]

[W2] Leveraging Class Hierarchy in Fashion Classification [paper]

[W1] Stochastic Relational Network [paper]

Domestic Conferences

[D1] FastText를 적용한 한국어 단어 임베딩 [paper]