Social Pressure Breaks Majority Voting in LLM Safety Panels

Large language models (LLMs) are increasingly used to detect unsafe content. A common approach is to combine judgments from a panel of models to correct individual mistakes, but this benefit may disappear when every model sees the same misleading context before voting.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

• llms
• safety