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

arXiv: https://arxiv.org/abs/2607.19257 · HTML: https://mlsanity.com/paper/2607.19257/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)
- [HalluLens: LLM Hallucination Benchmark](https://mlsanity.com/paper/2504.17550/) (2025)
- [NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities](https://mlsanity.com/paper/2407.11963/) (2024)
- [Interaction Context Often Increases Sycophancy in LLMs](https://mlsanity.com/paper/2509.12517/) (2025)
- [U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack](https://mlsanity.com/paper/2503.00353/) (2025)
- [How Many Instructions Can LLMs Follow at Once?](https://mlsanity.com/paper/2507.11538/) (2025)
- [A Controllable Examination for Long-Context Language Models](https://mlsanity.com/paper/2506.02921/) (2025)
- [When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following](https://mlsanity.com/paper/2509.21051/) (2025)
- [Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data](https://mlsanity.com/paper/2508.15793/) (2025)
- [Talking with Tables for Better LLM Factual Data Interactions](https://mlsanity.com/paper/2412.17189/) (2024)

## Built on by (most cited first, 1 of 1)

- [Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return](https://mlsanity.com/paper/2609.14758/) (2026)

## Abstract (arXiv)

Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models. Experiment 1 (960 calls/model) measures instruction-following decay as rule count N grows from 10 to 160, crossed with four formats and system-prompt vs. user-turn placement. Perfect-response rate collapses to zero by N=80 for every model, format, and placement. Placement produces effects at least as large as format at N=160 in most models, but the direction is model-specific. No model shows a reliable markdown advantage; one 35B model favors plain text instead. Experiment 2 (5,520 calls/model) measures recall accuracy, false-premise sycophancy, and absent-fact fabrication across a 2k-to-512k-token context ladder in the same four formats. Recall stays near ceiling through 64-128k tokens, then degrades sharply and format-dependently: one model's accuracy spread reaches 48 points at 128k tokens. Fabrication never occurs (0/5,760 probes), and sycophancy stays negligible (<=8.3%). What rises sharply near each model's context ceiling is outright refusal to answer (0% to 79-90%), distinct from sycophancy or fabrication. Neither pre-registered format ordering holds, and token overhead (+22% to +37% over plain text) further changes which format is preferable where accuracy spread is genuine. We release the full harness, corpus generator, and raw results (VeyraBench): https://github.com/iNetanel/veyrabench