A Language Model's Guide Through Latent Space
Paper
•
2402.14433
•
Published
•
1
Understanding LLM
-
-
The Hidden Space of Transformer Language Adapters
Paper • 2402.13137 • Published -
Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models
Paper • 2402.16438 • Published -
AtP*: An efficient and scalable method for localizing LLM behaviour to components
Paper • 2403.00745 • Published • 8 -
Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral
Paper • 2403.01851 • Published -
The Hidden Attention of Mamba Models
Paper • 2403.01590 • Published -
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Paper • 2403.03853 • Published • 61 -
In-Context Learning Creates Task Vectors
Paper • 2310.15916 • Published • 39 -
Function Vectors in Large Language Models
Paper • 2310.15213 • Published • 1 -
Localizing Paragraph Memorization in Language Models
Paper • 2403.19851 • Published • 13 -
ROME: Memorization Insights from Text, Probability and Hidden State in Large Language Models
Paper • 2403.00510 • Published -
Large Language Models Struggle to Learn Long-Tail Knowledge
Paper • 2211.08411 • Published • 3 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 74 -
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
Paper • 2406.11813 • Published • 27 -
Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
Paper • 2406.12649 • Published • 14