LLMs display prompt-sensitive risk behavior and a linearly decodable realization-status signal in Gemma's residual stream, yet activation steering along this direction fails to shift downstream risk choices.
Can ai language models replace human participants?Trends in Cognitive Sciences, 27(7):597–600, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Representation Without Control: Testing the Realization Effect in Language Models
LLMs display prompt-sensitive risk behavior and a linearly decodable realization-status signal in Gemma's residual stream, yet activation steering along this direction fails to shift downstream risk choices.