Implicitly conveying a user's professional role in multi-turn LLM conversations shifts moral wrongness ratings across ten common-morality rules in two non-reasoning models.
Representation engineering: A top-down approach to ai transparency, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
User identity conditions moral wrongness ratings in non-reasoning large language models
Implicitly conveying a user's professional role in multi-turn LLM conversations shifts moral wrongness ratings across ten common-morality rules in two non-reasoning models.