ValueLocate identifies value neurons via activation probability differences between opposing value prompts, and amplifying or suppressing these neurons alters G-EVAL value scores in four LLMs.
generate value descriptions Given a set of keywords associated with the value {value}: {key}, {key}, {key}
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
ValueLocate identifies value neurons via activation probability differences between opposing value prompts, and amplifying or suppressing these neurons alters G-EVAL value scores in four LLMs.