RoleRAG tunes only role-token embeddings on a frozen LLM to run six RAG sub-tasks, reporting improved QA accuracy, but with inconsistent headline numbers and no significance tests.
Knoblock, and Wei - Min Shen
1 Pith paper cite this work, alongside 370 external citations. Polarity classification is still indexing.
1
Pith paper citing it
370
external citations · OpenAlex
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization
RoleRAG tunes only role-token embeddings on a frozen LLM to run six RAG sub-tasks, reporting improved QA accuracy, but with inconsistent headline numbers and no significance tests.