Most tested LLMs adjust their expressed values to a user's age and education, but consistency between explicit profile and dialogue-history conditions varies across models.
proposed_question
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
-
Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History
Most tested LLMs adjust their expressed values to a user's age and education, but consistency between explicit profile and dialogue-history conditions varies across models.