Question about scoring function about colbert

[okhat]

That's indeed a good edge case to keep in mind — thanks! Since we care about the largest/max similarities per query token for the high-scoring documents, these are practically always positive. But we might want to enforce this more directly with a ReLU before the max sim.

[zhiqihuang]

It is based on your similarity function. L2 is always positive, but cosine similarity could be negative. I agree with you that all negative similarities are definitely a concern case.