English

Instruction Complexity Induces Positional Collapse in Adversarial LLM Evaluation

Computation and Language 2026-05-01 v1 Artificial Intelligence

Abstract

When instructed to underperform on multiple-choice evaluations, do language models engage with question content or fall back on positional shortcuts? We map the boundary between these regimes using a six-condition adversarial instruction-specificity gradient administered to two instruction-tuned LLMs (Llama-3-8B and Llama-3.1-8B) on 2,000 MMLU-Pro items. Distributional screening (response-position entropy) and an independent content-engagement criterion (difficulty-accuracy correlation) jointly characterise each condition. The gradient reveals three regimes rather than a monotonic transition. Vague adversarial instructions produce moderate accuracy reduction with preserved content engagement. Standard sandbagging and capability-imitation instructions produce positional entropy collapse with partial content engagement. A two-step answer-aware avoidance instruction produces extreme positional collapse, with near-total concentration on a single response position (99.9% and 87.4%) and no measurable content sensitivity. This was the only multi-step instruction tested, and it produced the most extreme shortcut. The attractor position matches each model's content-absent null-prompt default. The effect replicates across both models and four academic domains. Distributional collapse and content engagement can co-occur (50% concordance between screening criteria), indicating that entropy-based screening and difficulty-based content assessment capture partially independent dimensions of response validity. Results suggest that instruction complexity can determine whether adversarial compliance uses content-aware or content-blind mechanisms in small instruction-tuned LLMs under greedy decoding.

Keywords

Cite

@article{arxiv.2604.27249,
  title  = {Instruction Complexity Induces Positional Collapse in Adversarial LLM Evaluation},
  author = {Jon-Paul Cacioli},
  journal= {arXiv preprint arXiv:2604.27249},
  year   = {2026}
}

Comments

12 pages, 3 figures, 3 tables. Pre-registered on OSF (osf.io/7p64)

R2 v1 2026-07-01T12:42:30.443Z