A bidirectional RL framework jointly optimizes LLM query and document augmentation and improves retrieval accuracy on BEIR benchmarks beyond query-only rewriting.
The snowflake elastic data warehouse
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
-
Harnessing the Power of Reinforcement Learning for Language-Model-Based Information Retriever via Query-Document Co-Augmentation
A bidirectional RL framework jointly optimizes LLM query and document augmentation and improves retrieval accuracy on BEIR benchmarks beyond query-only rewriting.