PRIME: Evaluating Prompt Resolution Under Incompatible Instructions in LLMs

Large language models (LLMs) often encounter conflicting prompts, although current instruction following benchmarks assess those meta-instructions in isolation, limiting the insights about how models process conflicting instructions. We introduce a framework textitPRIME(textitPrompt Resolution under Incompatible Meta-Instructions Evaluation) to analyze behavior of LLMs when provided with conflicting instructions. textitPRIME purposefully produces calibrated conflicts across response length, output format, and reasoning; classifying model responses with a deterministic behavioral taxonomy. We are evaluating five instruction tuned open weight LLMs in two distinct settings, balanced and naturally distributed. The conclusion we reach upon analysis is that conflict type is more significant in affecting behavior than model scale, and various failure modes across different categories of conflict. Our findings emphasize the value of developing conflict awareness and suggest ability of LLM to follow instructions cannot be assessed through isolated constraints alone.