Computation and Language · Computer Science
Less is More: Local Intrinsic Dimensions of Contextual Language Models
Benjamin Matthias Ruppik, Julius von Rohrscheidt, Carel van Niekerk, Michael Heck +7
2025-10-28
Computation and Language · Computer Science
Unveiling the Generalization Power of Fine-Tuned Large Language Models
Haoran Yang, Yumeng Zhang, Jiaqi Xu, Hongyuan Lu +2
2024-03-15
Computation and Language · Computer Science
Understanding the Effects of Domain Finetuning on LLMs
Eshaan Tanwar, Deepak Nathani, William Yang Wang, Tanmoy Chakraborty
2025-10-13
Computation and Language · Computer Science
Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
Wenke Huang, Jian Liang, Zekun Shi, Didi Zhu +5
2024-11-19
Artificial Intelligence · Computer Science
Do LLMs "know" internally when they follow instructions?
Juyeon Heo, Christina Heinze-Deml, Oussama Elachqar, Kwan Ho Ryan Chan +4
2025-03-31
Computation and Language · Computer Science
Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models
Iuri Macocco, Nora Graichen, Gemma Boleda, Marco Baroni
2025-10-06
Machine Learning · Computer Science
Layer by Layer: Uncovering Hidden Representations in Language Models
Oscar Skean, Md Rifat Arefin, Dan Zhao, Niket Patel +3
2025-06-17
Computation and Language · Computer Science
"Why" Has the Least Side Effect on Model Editing
Tsung-Hsuan Pan, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
2024-09-30
Machine Learning · Computer Science
Does Representation Matter? Exploring Intermediate Layers in Large Language Models
Oscar Skean, Md Rifat Arefin, Yann LeCun, Ravid Shwartz-Ziv
2024-12-13
Artificial Intelligence · Computer Science
Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models
Hirohane Takagi, Gouki Minegishi, Shota Kizawa, Issey Sukeda +1
2025-11-11
Computation and Language · Computer Science
Outliers Dimensions that Disrupt Transformers Are Driven by Frequency
Giovanni Puccetti, Anna Rogers, Aleksandr Drozd, Felice Dell'Orletta
2024-06-19
Computation and Language · Computer Science
How does fine-tuning improve sensorimotor representations in large language models?
Minghua Wu, Javier Conde, Pedro Reviriego, Marc Brysbaert
2026-03-05
Computation and Language · Computer Science
Chained Tuning Leads to Biased Forgetting
Megan Ung, Alicia Sun, Samuel J. Bell, Bhaktipriya Radharapu +2
2024-12-30
Computation and Language · Computer Science
Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model
Wenke Huang, Jian Liang, Xianda Guo, Yiyang Fang +13
2025-03-07
Computation and Language · Computer Science
Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity
Katharina Hämmerl, Alina Fastowski, Jindřich Libovický, Alexander Fraser
2023-06-08
Computation and Language · Computer Science
Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks
Zhiwen Ruan, Yun Chen, Yutao Hou, Peng Li +2
2025-09-30
Computation and Language · Computer Science
Understanding Privacy Risks of Embeddings Induced by Large Language Models
Zhihao Zhu, Ninglu Shao, Defu Lian, Chenwang Wu +3
2024-04-26