Training-free methods for LLM trustworthiness show inconsistent results across dimensions, with clear trade-offs in utility, robustness, and overhead depending on where they intervene during inference.
Towards inference-time category- wise safety steering for large language models.CoRR, abs/2410.01174
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Systematic Study of Training-Free Methods for Trustworthy Large Language Models
Training-free methods for LLM trustworthiness show inconsistent results across dimensions, with clear trade-offs in utility, robustness, and overhead depending on where they intervene during inference.