Aligning VLM Assistants with Personalized Situated Cognition
Journal:
arXiv
Published Date:
Jun 1, 2025
Abstract
Vision-language models (VLMs) aligned with general human objectives, such as
being harmless and hallucination-free, have become valuable assistants of
humans in managing visual tasks. However, people with diversified backgrounds
have different cognition even in the same situation. Consequently, they may
have personalized expectations for VLM assistants. This highlights the urgent
need to align VLM assistants with personalized situated cognition for
real-world assistance. To study this problem, we first simplify it by
characterizing individuals based on the sociological concept of Role-Set. Then,
we propose to evaluate the individuals' actions to examine whether the
personalized alignment is achieved. Further, we construct a benchmark named
PCogAlignBench, which includes 18k instances and 20 individuals with different
Role-Sets. Finally, we present a framework called PCogAlign, which constructs a
cognition-aware and action-based reward model for personalized alignment.
Experimental results and human evaluations demonstrate the reliability of the
PCogAlignBench and the effectiveness of our proposed PCogAlign. We will
open-source the constructed benchmark and code at
https://github.com/NLPGM/PCogAlign.
