Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation
Read the original on arXiv Computation and Language →The paper investigates how annotator-style rebuttals can manipulate large language model (LLM) moderation systems, either by whitewashing hateful content as normal or smearing normal content as hateful. Using a rejudge protocol that adds decision‑boundary perturbations and adversarial rationales, the authors show that such rebuttals significantly degrade moderation performance, especially in multi‑turn settings. The study finds consistent, model‑specific asymmetries between the two manipulation directions and demonstrates that explicit reasoning prompts and defensive instructions mitigate but do not eliminate the vulnerability.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.