Document optimization via GRPO fine-tuning transforms documents to improve black-box retrieval, enabling smaller models to outperform larger ones on code and VDR benchmarks.
Deltas are absolute changes relative to the corresponding Direct Retrieval row
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Document Optimization for Black-Box Retrieval via Reinforcement Learning
Document optimization via GRPO fine-tuning transforms documents to improve black-box retrieval, enabling smaller models to outperform larger ones on code and VDR benchmarks.