{"total":23,"rows":[{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2302.00070","title":"Debiasing Vision-Language Models via Biased Prompts","created":"2023-01-31","cited_by_count":149,"area":"mllm"},{"id":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104,"area":"mllm"},{"id":"2406.12030","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","created":"2024-06-17","cited_by_count":85,"area":"mllm"},{"id":"2306.12424","title":"VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution","created":"2023-06-21","cited_by_count":52,"area":"mllm"},{"id":"2404.10618","title":"Private Attribute Inference from Images with Vision-Language Models","created":"2024-04-16","cited_by_count":37,"area":"mllm"},{"id":"2403.17830","title":"Assessment of Multimodal Large Language Models in Alignment with Human Values","created":"2024-03-26","cited_by_count":36,"area":"mllm"},{"id":"2411.00997","title":"Identifying Implicit Social Biases in Vision-Language Models","created":"2024-11-01","cited_by_count":27,"area":"mllm"},{"id":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"id":"2411.04420","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","created":"2024-11-07","cited_by_count":17,"area":"mllm"},{"id":"2404.00860","title":"Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance","created":"2024-04-01","cited_by_count":14,"area":"mllm"},{"id":"2307.12980","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","created":"2023-07-24","cited_by_count":12,"area":"mllm"},{"id":"2410.12722","title":"WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluation","created":"2024-10-16","cited_by_count":11,"area":"mllm"},{"id":"2407.08970","title":"Self-interpreting Adversarial Images","created":"2024-07-12","cited_by_count":7,"area":"mllm"},{"id":"2504.03440","title":"Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Models","created":"2025-04-04","cited_by_count":6,"area":"mllm"},{"id":"2509.23827","title":"Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models","created":"2025-09-28","cited_by_count":6,"area":"mllm"},{"id":"2601.06460","title":"Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs","created":"2026-01-10","cited_by_count":4,"area":"mllm"},{"id":"2409.15256","title":"Behavioral Bias of Vision-Language Models: A Behavioral Finance View","created":"2024-09-23","cited_by_count":3,"area":"mllm"},{"id":"2503.22941","title":"Identifying Multi-modal Knowledge Neurons in Pretrained Transformers via Two-stage Filtering","created":"2025-03-29","cited_by_count":3,"area":"mllm"},{"id":"2512.15926","title":"DSO: Direct Steering Optimization for Bias Mitigation","created":"2025-12-17","cited_by_count":3,"area":"mllm"},{"id":"2604.18803","title":"LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models","created":"2026-04-20","cited_by_count":3,"area":"mllm"},{"id":"2509.15478","title":"Red Teaming Multimodal Language Models: Evaluating Harm Across Prompt Modalities and Models","created":"2025-09-18","cited_by_count":1,"area":"mllm"},{"id":"2602.04739","title":"Alignment Drift in Multimodal LLMs: A Two-Phase, Longitudinal Evaluation of Harm Across Eight Model Releases","created":"2026-02-04","cited_by_count":0,"area":"mllm"}],"next_cursor":null}