Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation
Bingzhe Wu, Haotian Lu, Yuchen Mou
Current large language models (LLMs), even those explicitly trained for reasoning, often struggle with ambiguous content moderation cases due to misleading "decision shortcuts" emb…
cs.AI2026
CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs
Haotian Lu, Yuchen Mou, Bingzhe Wu
Content moderation in online platforms faces persistent challenges due to the evolving complexity of user-generated content and the limitations of traditional rule-based and machin…