In the news
Where Should a Document Live: Context, Representations, or Parameters?
arXiv cs.AI · Published · 3 min read
In 30 seconds
- What happened
- Researchers compared three methods for giving LLMs access to new documents: context windows, fine-tuned parameters, and cached representations, finding representation-based methods most accurate.
- Why it matters
- Engineers building retrieval-augmented systems or knowledge-intensive applications need to choose between in-context, parametric, and representation injection approaches.
- Watch out
- Representation methods show catastrophic forgetting on unrelated tasks, degrading performance by six percent generally and thirteen percent on coding benchmarks.
- llm
- language model
- context window
- fine-tun
- edge
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.