Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment

Research Hugging Face Papers Source language: Chinese

论文摘要(作者报告,未经本站复测):Abstention, the withholding of a response by a large language model (LLM) under uncertainty or safety risks, is essential for trustworthy models.

Excerpt

论文摘要(作者报告,未经本站复测):Abstention, the withholding of a response by a large language model (LLM) under uncertainty or safety risks, is essential for trustworthy models.

Short excerpt from the source — open the original for the full text.

Sources

← Back to the daily brief