MetaSC improves language model safety by using a meta-critic to iteratively rewrite the safety specification that guides self-critique at inference time.
Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MetaSC: Test-Time Safety Specification Optimization for Language Models
MetaSC improves language model safety by using a meta-critic to iteratively rewrite the safety specification that guides self-critique at inference time.