How can we distinguish between legitimate persuasion and manipulative influence in deliberative settings?

Google’s guide defining adversarial testing as systematically evaluating ML models against malicious or inadvertently harmful input, covering explicit queries (containing policy-violating language) and implicit queries (seeming harmless but involving sensitive topics). The four-stage workflow inv...

Sortition algorithms have been designed to select participants according to quotas, balancing representativeness, fairness and manipulation resistance (Flanigan, 2021; Baharav, 2024).