Retrieval with Learned Similarities — mentioned by lunarmony

Sat, 30 Aug 2025 03:54:38 GMT

Researchers have discussed limitations of vector-based retrieval from a rank perspective in various forms for a few years. It's further been shown that better alternative exists; some low-rank approaches can theoretically approximate arbitrary high-rank distribution while permitting MIPS-level efficient inference (see e.g., Retrieval with Learned Similarities, https://arxiv.org/abs/2407.15462). Such solutions are already being used in production at Meta and at LinkedIn.

Paper and discussion history. A mention is not an endorsement.

Retrieval with Learned Similarities · HackerPapers discussions

Retrieval with Learned Similarities — mentioned by lunarmony