Somehow missed this thread from @sungkim.bsky.social --- thanks for the interest in our work!
Reposted from
Sung Kim
Oh wow!
A surprising result from Databricks when measuring embeddings and rerankers on internal evals.
1- Reranking few docs improves recall (expected).
2- Reranking many docs degrades quality (!).
3- Reranking too many documents is quite often worse than using embedding model alone (!!).
A surprising result from Databricks when measuring embeddings and rerankers on internal evals.
1- Reranking few docs improves recall (expected).
2- Reranking many docs degrades quality (!).
3- Reranking too many documents is quite often worse than using embedding model alone (!!).
Comments