2 papers
cs.LG2026
Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
Cristian Hinostroza, Rodrigo Toro Icarte, Christ Devia +4
Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more interpretable and optimized arc…
cs.LG2024
Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures
Jorge F. Silva, Victor Faraggi, Camilo Ramirez +2
We present new results to model and understand the role of encoder-decoder design in machine learning (ML) from an information-theoretic angle. We use two main information concepts…