1 citations · 1 across the 4 of their papers we have counts for
5 papers
How Does Unfaithful Reasoning Emerge from Autoregressive Training? A Study of Synthetic Experiments
Fuxin Wang, Amr Alazali, Yiqiao Zhong
Chain-of-thought (CoT) reasoning generated by large language models (LLMs) is often unfaithful: intermediate steps can be logically inconsistent or fail to reflect the causal relat…
Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
Xingyu Zhao, Darsh Sharma, Rheeya Uppaal +1
Large language models (LLMs) often achieve strong benchmark accuracy yet remain brittle under small distribution shifts. While recent mechanistic studies reveal the discrepancy bet…
Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
Haolin Yang, Hakaze Cho, Yiqiao Zhong +1
The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either speci…
A statistical theory of overfitting for imbalanced classification
Jingyang Lyu, Kangjie Zhou, Yiqiao Zhong
Classification with imbalanced data is a common challenge in data analysis, where certain classes (minority classes) account for a small fraction of the training data compared with…
Assessing and improving reliability of neighbor embedding methods: a map-continuity perspective
Zhexuan Liu, Rong Ma, Yiqiao Zhong
Visualizing high-dimensional data is essential for understanding biomedical data and deep learning models. Neighbor embedding methods, such as t-SNE and UMAP, are widely used but c…