Megadose AI progress, ranked and analyzed.

Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models

· ArXiv · AI/CL/LG ·
Instruction adherence broke down completely once prompts carried 80 rules.

The paper reports two controlled experiments across five models using a synthetic corpus called the Book of Veyra. Formatting did not produce a reliable markdown advantage, and prompt placement sometimes mattered as much as format. Long-context recall held up through roughly 64k-128k tokens, then fell sharply depending on model and format. The study found no fabrication in its probes, but refusals rose near context limits. ArXiv · AI/CL/LG's note

score 6

Categories: Research