HCOMP 2026 Paper: Fluent LLM Experiments Breed Overreliance in Content Moderation

An HCOMP 2026 Honorable Mention paper finds that the more fluent and readable LLM explanations are, the more content moderators overrely on them, raising concerns about human-AI collaboration in trust and safety.

2026-09-30 ~ 2026-09-30 · 2 related posts

• HCOMP paper: fluent LLM explanations drive over-reliance in hate speech moderation — windx0303 · 2026-09-30

1 near-duplicate retellings: windx0303