CIDER: A Causal Cure for Brand-Obsessed Text-to-Image Models
Text-to-image (T2I) models exhibit a significant yet under-explored "brand bias", a tendency to generate contents featuring dominant commercial brands from generic prompts, posing ethical and legal risks. We propose CIDER, a novel, model-agnostic framework to mitigate bias at inference-time through prompt refinement to avoid costly retraining. CIDER uses a lightweight detector to identify branded content and a Vision-Language Model (VLM) to generate stylistically divergent alternatives. We introduce the Brand Neutrality Score (BNS) to quantify this issue and perform extensive experiments on leading T2I models. Results show CIDER significantly reduces both explicit and implicit biases while maintaining image quality and aesthetic appeal. Our work offers a practical solution for more original and equitable content, contributing to the development of trustworthy generative AI.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection
Despite the rapid progress of multimodal large language models in building Graphical User Interface (GUI) agents, their real-world task completion is fundamentally bottlenecked by a lack of world knowledge about GUI oper…
Reinforcement LearningCIDER: Commonsense Inference for Dialogue Explanation and Reasoning
Commonsense inference to understand and explain human language is a fundamental research problem in natural language processing. Explaining human conversations poses a great challenge as it requires contextual understand…
Natural Language InferenceTowards Robust Multimodal Emotion Recognition under Missing Modalities and Distribution Shifts
Recent advancements in Multimodal Emotion Recognition (MER) face challenges in addressing both modality missing and Out-Of-Distribution (OOD) data simultaneously. Existing methods often rely on specific models or introdu…
Causal InferencecounterfactualEmotion RecognitionMultimodal Emotion RecognitionDeconfounded Image Captioning: A Causal Retrospect
Dataset bias in vision-language tasks is becoming one of the main problems which hinders the progress of our community. Existing solutions lack a principled analysis about why modern image captioners easily collapse into…
Causal InferenceImage CaptioningSingle Headed Attention RNN: Stop Thinking With Your Head
The leading approaches in language modeling are all obsessed with TV shows of my youth - namely Transformers and Sesame Street. Transformers this, Transformers that, and over here a bonfire worth of GPU-TPU-neuromorphic …
GPUHyperparameter OptimizationLanguage ModelingLanguage Modelling