SOURCE-LINKED INTELLIGENCE

Where Should a Document Live: Context, Representations, or Parameters?

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the context window as documents, encoded into the model's parameters, or injected as latent representations. However, each of these methods comes with different efficiency, cost, and performance trade-offs, with no single winner. We present a controlled comparison of representation-based (KV-cache based) and parametric (fine-tuning-based) adaptation methods on five knowledge-intensive benchmarks. We show that in the oracle setting, Cartridges (KV) are t

Read original source ↗ Open in workspace

recordType

paper

region

Global