Graph-GRPO builds a dependency graph over CoT steps and propagates outcome rewards to enable finer credit assignment in generative relevance modeling for e-commerce search.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance
Graph-GRPO builds a dependency graph over CoT steps and propagates outcome rewards to enable finer credit assignment in generative relevance modeling for e-commerce search.