4 papers
When LRP Diverges from Leave-One-Out in Transformers
Weiqiu You, Siqi Zeng, Yao-Hung Hubert Tsai +2
Leave-One-Out (LOO) provides an intuitive measure of feature importance but is computationally prohibitive. While Layer-Wise Relevance Propagation (LRP) offers a potentially effici…
Brain-Inspired Stochastic Joint Embedding Representation Learning
Makoto Yamada, Kian Ming A. Chai, Ayoub Rhim +3
Representation learning is one of the key research topics in machine learning, and the framework of self-supervised learning (SSL) has revolutionized computer vision. However, thes…
Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
Siqi Zeng, Yifei He, Meitong Liu +5
Task arithmetic, representing downstream tasks through linear operations on task vectors, has emerged as a simple yet powerful paradigm for transferring knowledge across diverse se…
On Verbalized Confidence Scores for LLMs
Daniel Yang, Yao-Hung Hubert Tsai, Makoto Yamada
The rise of large language models (LLMs) and their tight integration into our daily life make it essential to dedicate efforts towards their trustworthiness. Uncertainty quantifica…