A mean-field kinetic theory derivation produces a closed-form U-shaped token retrieval profile that explains the lost-in-the-middle phenomenon in Transformers.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Duality-based analysis yields fluctuation-scale O(N^{-1/2}) mean-field convergence for L2 interactions and optimal O(N^{-1}) rates plus correlation bounds under higher regularity via iterative dual cumulants.
Reduced SPDE models for co-evolving opinion dynamics capture clustering behavior efficiently with lower cost than full-state models.
citing papers explorer
-
Kinetic theory for Transformers and the lost-in-the-middle phenomenon
A mean-field kinetic theory derivation produces a closed-form U-shaped token retrieval profile that explains the lost-in-the-middle phenomenon in Transformers.
-
Quantitative Estimates for Mean-Field Limits and Correlation Functions through a Duality Framework
Duality-based analysis yields fluctuation-scale O(N^{-1/2}) mean-field convergence for L2 interactions and optimal O(N^{-1}) rates plus correlation bounds under higher regularity via iterative dual cumulants.
-
Clustering in co-evolving opinion dynamics: reduced SPDE models
Reduced SPDE models for co-evolving opinion dynamics capture clustering behavior efficiently with lower cost than full-state models.