CLEAR: Character Unlearning in Textual and Visual Modalities

ACL ARR 2025 February Submission7781 Authors

Abstract: Machine Unlearning (MU) is critical for removing private or hazardous information from deep learning models. While MU has advanced significantly in unimodal (text or vision) settings, multimodal unlearning (MMU) remains underexplored due to the lack of open benchmarks for evaluating cross-modal data removal. To address this gap, we introduce CLEAR, the first open-source benchmark designed specifically for MMU. CLEAR contains 200 fictitious individuals and 3,700 images linked with corresponding question-answer pairs, enabling a thorough evaluation across modalities. We conduct a comprehensive analysis of 11 MU methods (e.g., SCRUB, gradient ascent, DPO) across four evaluation sets, demonstrating that jointly unlearning both modalities outperforms single-modality approaches.

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: multimodality,vision question answering, benchmarking

Contribution Types: Data resources

Languages Studied: english

Submission Number: 7781