Recall@1
A commonly used evaluation metric in retrieval tasks that measures the probability that the most similar sample returned by a model is ranked first, i.e., that it is the correct pairing.
Timeline (last 90 days)
The evaluation metrics include raw Recall@1 (measuring direct retrieval capability) and paired token cosine similarity (measuring the consistency of latent coordinates).
The experimental results show that even with identical inputs, the raw Recall@1 between latent representations produced by different schemas is only 5.9%–17.7%.
Using only 64 paired segments, raw Recall@1 can be raised to 88.4%–90.3%, and token cosine similarity to about 0.82.
All Facts (3)
The evaluation metrics include raw Recall@1 (measuring direct retrieval capability) and paired token cosine similarity (measuring the consistency of latent coordinates).
50%UnverifiedThe experimental results show that even with identical inputs, the raw Recall@1 between latent representations produced by different schemas is only 5.9%–17.7%.
50%UnverifiedUsing only 64 paired segments, raw Recall@1 can be raised to 88.4%–90.3%, and token cosine similarity to about 0.82.
50%