Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History
This work addresses the need for robust adaptation in LLMs for real-world applications, though it is incremental as it builds on existing evaluation methods.
The paper tackled the problem of evaluating how large language models adapt their responses to users' sociodemographic factors, finding that most models adjust expressed values based on demographic changes, with stronger reasoning models showing greater consistency.
Effective engagement by large language models (LLMs) requires adapting responses to users' sociodemographic characteristics, such as age, occupation, and education level. While many real-world applications leverage dialogue history for contextualization, existing evaluations of LLMs' behavioral adaptation often focus on single-turn prompts. In this paper, we propose a framework to evaluate LLM adaptation when attributes are introduced either (1) explicitly via user profiles in the prompt or (2) implicitly through multi-turn dialogue history. We assess the consistency of model behavior across these modalities. Using a multi-agent pipeline, we construct a synthetic dataset pairing dialogue histories with distinct user profiles and employ questions from the Value Survey Module (VSM 2013) (Hofstede and Hofstede, 2016) to probe value expression. Our findings indicate that most models adjust their expressed values in response to demographic changes, particularly in age and education level, but consistency varies. Models with stronger reasoning capabilities demonstrate greater alignment, indicating the importance of reasoning in robust sociodemographic adaptation.