7 papers
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
Sungjun Lim, Heedong Kim, Andrew Lee +1
Mechanistic interpretability aims to explain a model's behavior by identifying causally responsible internal structures. Dictionary-based explainers such as sparse autoencoders and…
Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach
Youngjun Choi, Joonseong Kang, Sungjun Lim +1
Data valuation has become central in the era of data-centric AI. It drives efficient training pipelines and enables objective pricing in data markets by assigning a numeric value t…
Semi-Supervised Preference Optimization with Limited Feedback
Seonggyun Lee, Sungjun Lim, Seojin Park +2
The field of preference optimization has made outstanding contributions to the alignment of language models with human preferences. Despite these advancements, recent methods still…
Uncertainty-driven Embedding Convolution
Sungjun Lim, Kangjun Noh, Youngjun Choi +2
Text embeddings are essential components in modern NLP pipelines. Although numerous embedding models have been proposed, no single model consistently dominates across domains and t…
Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts
Hojun Jin, Eunsoo Hong, Ziwon Hyung +3
Hard-parameter sharing is a common strategy to train a single model jointly across diverse tasks. However, this often leads to task interference, impeding overall model performance…
Flat Posterior Does Matter For Bayesian Model Averaging
Sungjun Lim, Jeyoon Yeom, Sooyon Kim +5
Bayesian neural networks (BNNs) estimate the posterior distribution of model parameters and utilize posterior samples for Bayesian Model Averaging (BMA) in prediction. However, des…