adversarial bias 1audit-based reinforcement learning 1contextual bandits 1regret analysis 1social feedback 1trust learning 1
From the 1 of 4 linked papers with an AI index.
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Learning When to Trust in Contextual Social Bandits
Majid Ghasemi, Mark Crowley
The paper studies bandit learning where feedback providers are honest in some contexts but biased in others (contextual sycophancy) and shows that without occasional ground‑truth a…
cs.AI2026
Objective Decoupling in Social Reinforcement Learning: Recovering Ground Truth from Sycophantic Majorities
Majid Ghasemi, Mark Crowley
Contemporary AI alignment strategies rely on a fragile premise: that human feedback, while noisy, remains a fundamentally truthful signal. In this paper, we identify this assumptio…