Lost in the Middle (Positional Bias)
LLM accuracy on retrieving information from long contexts drops sharply when relevant content sits in the middle of the prompt rather than at the start or end.
Problem
The model exhibits a U-shaped attention curve: content at the start (primacy) and end (recency) of the prompt is retrieved well; content in the middle is poorly retrieved. The team feeds RAG chunks ordered by relevance — relevant chunks end up in the middle of the prompt — and the model misses them. Distinct from context-fragmentation (which is about simultaneous holding of constraints) by being positional, not relational.
Solution
Acknowledge the bias as architectural. Pair with: landmark-attention (architectural mitigation, requires model support), information-chunking-memory (preprocessing mitigation), context-window-packing (positional design), context-window-dumb-zone (related utilization limit).
When to use
- Never as an unaddressed state. Cite when reviewing long-context RAG or document-QA agents.
- Surface in eval design to test middle-of-prompt retrieval explicitly.
- Use as the rationale for prompt-ordering or landmark-attention adoption.
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.