🛰️ Daily AI Frontier
‹ back to 2026-09-16

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

Research LLMs & Foundation Models

Ranking

Overall 82
Content 100
Popularity 39

Observed public metrics from 1 member.

Merged summary

TL;DR - This paper compares storing new knowledge in LLM context, KV-cache representations, or fine-tuned parameters. KV-based Cartridges deliver the strongest accuracy and retrieval performance but can cause substantial catastrophic forgetting.

  • In oracle tests across five knowledge-intensive benchmarks, Cartridges outperform parametric methods by roughly 10 points at nearly every storage budget.
  • KV Compaction remains competitive only at low compression, trailing parametric methods by 10 points beyond (50\times) compression.
  • In multi-document retrieval, Cartridges alone match in-context learning, beating parametric methods by 29 points and Compaction by 15 points.
  • Cartridges reduce control-benchmark performance by 6%, including a 13% decline on coding tasks.

Sources (1)

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

arXiv cs.CL Nathanaël Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias, Adrià de Gispert 2026-09-15 arXiv:2609.17346
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-22 14:21:08.357788 UTC

TL;DR - This paper compares storing new knowledge in LLM context, KV-cache representations, or fine-tuned parameters. KV-based Cartridges deliver the strongest accuracy and retrieval performance but can cause substantial catastrophic forgetting.

  • In oracle tests across five knowledge-intensive benchmarks, Cartridges outperform parametric methods by roughly 10 points at nearly every storage budget.
  • KV Compaction remains competitive only at low compression, trailing parametric methods by 10 points beyond (50\times) compression.
  • In multi-document retrieval, Cartridges alone match in-context learning, beating parametric methods by 29 points and Compaction by 15 points.
  • Cartridges reduce control-benchmark performance by 6%, including a 13% decline on coding tasks.
item →