Investigating Associational Biases in Inter-Model Communication of Large Generative Models

TL;DR

This paper investigates how inter-model communication in generative AI can propagate and amplify associational biases, especially in human activity and affect recognition, revealing demographic drifts and proposing mitigation strategies.

Contribution

It introduces a systematic analysis of demographic bias evolution in inter-model pipelines for human-centric tasks and proposes mitigation approaches.

Findings

Demographic drifts toward younger and female-presenting representations.

Biases supported by spurious visual cues like background or hair.

Identifies potential for bias amplification across model exchanges.

Abstract

Social bias in generative AI can manifest not only as performance disparities but also as associational bias, whereby models learn and reproduce stereotypical associations between concepts and demographic groups, even in the absence of explicit demographic information (e.g., associating doctors with men). These associations can persist, propagate, and potentially amplify across repeated exchanges in inter-model communication pipelines, where one generative model's output becomes another's input. This is especially salient for human-centred perception tasks, such as human activity recognition and affect prediction, where inferences about behaviour and internal states can lead to errors or stereotypical associations that propagate into unequal treatment. In this work, focusing on human activity and affective expression, we study how such associations evolve within an inter-model communication pipeline that alternates between image generation and image description. Using the RAF-DB and PHASE datasets, we quantify demographic distribution drift induced by model-to-model information exchange and assess whether these drifts are systematic using an explainability pipeline. Our results reveal demographic drifts toward younger representations for both actions and emotions, as well as toward more female-presenting representations, primarily for emotions. We further find evidence that some predictions are supported by spurious visual regions (e.g., background or hair) rather than concept-relevant cues (e.g., body or face). We also examine whether these demographic drifts translate into measurable differences in downstream behaviour, i.e., while predicting activity and emotion labels. Finally, we outline mitigation strategies spanning data-centric, training and deployment interventions, and emphasise the need for careful safeguards when deploying interconnected models in human-centred AI systems.