Robustness in dense retrieval follows power-law scaling laws, but with different exponents than effectiveness, and an adaptive weighting method (Pareto training) can improve the joint tradeoff more efficiently than scaling alone.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Scaling of Robustness and Effectiveness in Dense Retrieval
Robustness in dense retrieval follows power-law scaling laws, but with different exponents than effectiveness, and an adaptive weighting method (Pareto training) can improve the joint tradeoff more efficiently than scaling alone.