On long-context document tasks, heuristic prompt-injection attacks substantially increase attack success rate over no-attack baselines, and Authority spoof is generally the strongest listed heuristic.

CiteArk Verification Engine

4fdd6909ff

Approximate reconstruction: DeepSeek checkpoint instead of paper-listed Llama-3.1-8B-Instruct. · Synthetic independently generated panel of 20 instead of the unavailable paper corpus and reported 100 inputs. · Deterministic greedy generation and reconstructed prompts may differ from the paper's generation and prompt construction. · The observed value is recorded as directional evidence, but approximate reconstruction fidelity cannot establish a strict Match against the paper