liveBook · Manning

Relevance

As explained in Machines that Think

Relevance is the degree to which a response appropriately addresses the topic or requirements of an interaction.

Relevance concerns what matters in a particular context, but it does not have one universal meaning or measure. Human learning is shaped by consequences and stakes; language quality includes staying on topic; and attention mechanisms use scores to compare tokens. section 5.4.1 section 2.6.6 section 4.1.3

In self-attention, a token’s query is compared with other tokens’ keys using a dot product. The resulting scores indicate relative alignment in the model’s internal representations, not whether a response is relevant to a person’s needs. A softmax converts each row of scores into attention weights, which determine how much information the corresponding value vectors contribute. section 4.1.3

“Rises” and “sun”

The query for “rises” may align more strongly with the key for “sun” than with “the,” giving “sun” a higher relevance score and, after softmax, a greater attention weight. section 4.1.3

How Machines that Think covers it

How deep it goes
Explains query-key dot products, softmax weights, and value contributions, while distinguishing internal token scores from response quality.
Examples
Uses dialogue quality and the attention comparison between “rises,” “sun,” and “the.”
What you can do after
Understand how relevance differs across human learning, language quality, and attention scores.
How it connects
Connects relevance to human learning, objective functions, language evaluation, and self-attention.

Also explained in

Compare how 17 books explain relevance →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Machines that Think. The section links point to the parts of the book it draws on.