Comment

Comment by stared

While I like the idea of measuring subsequent steps, this kind of approach of using embeddings is the reason why I wrote: "Don't use cosine distance carelessly" (https://p.migdal.pl/blog/2025/01/dont-use-cosine-similarity).

In this case, cosine distance one would be in a case when it repeats word-by-word. It is not even a "similar thought" but some sort of LLM's OCD.

For anything else... cosine similarity says little. Sometimes, two steps can have opposite conclusions but have very high cosine similarity. In another case, it can just expand on the same solution but use different vocabulary or look from another angle.

A more robust approach would be to give the whole reasoning to an LLM and ask to grade according to a given criterion (e.g. "grade insight in each step, from 1 to 5").

parent stared 1 year ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton