LaRA shows that RAG versus long-context performance depends on model size, context length, task, and chunk settings, with no universal winner.
The Dark Lord
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing
LaRA shows that RAG versus long-context performance depends on model size, context length, task, and chunk settings, with no universal winner.