Explore >> Select a destination
|
You are here 
|
lh3.github.io | ||
| | | | |
mathematicaloddsandends.wordpress.com
|
|
| | | | | I recently came across this theorem on John Cook's blog that I wanted to keep for myself for future reference: Theorem. Let $latex f$ be a function so that $latex f^{(n+1)}$ is continuous on $latex [a,b]$ and satisfies $latex |f^{(n+1)}(x)| \leq M$. Let $latex p$ be a polynomial of degree $latex \leq n$ that interpolates... | |
| | | | |
destevez.net
|
|
| | | | | ||
| | | | |
swingleydev.com
|
|
| | | | | ||
| | | | |
www.shaped.ai
|
|
| | | This article explores how cross-encoders, long praised for their performance in neural ranking, may in fact be reimplementing classic information retrieval logic, specifically, a semantic variant of BM25. Through mechanistic interpretability techniques, the authors uncover circuits within MiniLM that correspond to term frequency, IDF, length normalization, and final relevance scoring. The findings bridge modern transformer-based relevance modeling with foundational IR principles, offering both theoretical insight and a roadmap for building more transparent and interpretable neural retrieval systems. | ||
