absorb.md

Msmarcominilml6v2

1 mentions across 0 people

Unknown speaker
paper · 2026-06-10
Recommended

“v2 is a fine-tuned ms-marco-MiniLM-L-6-v2 cross-encoder (22,713,601 parameters, measured from the released checkpoint) applied to the ten (query, memory) pairs that v1 has already selected; it does not change which ten memories are returned, so Recall@10 and Hit@10 are identical to v1 by construction, not by statistical coincidence.”

ConvMemory v2: A Recall-Preserving Reranker Significantly Improving Conversation ↗