Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and exposing source data on every call. We study an alternative: compiling a knowledge graph offline into a bank of LoRA adapters, one per entity, that serve as a parametric knowl...
Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov et al.· 0 citations
The results establish that parametric knowledge graph memory is feasible for storing knowledge, and identify selecting and composing the right adapters by a mechanism other than semantic similarity as the central open problem—motivating a learned, query-conditioned composition mechanism.
Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov et al.· 0 citations
A controlled study isolates the source of MADA-RL's gains: the counterfactual advantage produces the highest critic improvement rate of any model evaluated, indicating that trained critics learn to correct generator errors rather than to imitate them.
Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.