{"total":22,"rows":[{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82,"area":"mllm"},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72,"area":"mllm"},{"id":"2409.15310","title":"Visual Prompting in Multimodal Large Language Models: A Survey","created":"2024-09-05","cited_by_count":54,"area":"mllm"},{"id":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2505.11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","created":"2025-05-16","cited_by_count":19,"area":"mllm"},{"id":"2503.11832","title":"Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning","created":"2025-03-14","cited_by_count":16,"area":"mllm"},{"id":"2506.18322","title":"Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?","created":"2025-06-23","cited_by_count":14,"area":"mllm"},{"id":"2503.08884","title":"SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs","created":"2025-03-11","cited_by_count":7,"area":"mllm"},{"id":"2505.13946","title":"Visual Instruction Bottleneck Tuning","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2508.14264","title":"Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models","created":"2025-08-19","cited_by_count":5,"area":"mllm"},{"id":"2408.09111","title":"Measuring Agreeableness Bias in Multimodal Models","created":"2024-08-17","cited_by_count":4,"area":"mllm"},{"id":"2509.25178","title":"GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs","created":"2025-09-29","cited_by_count":4,"area":"mllm"},{"id":"2505.23065","title":"SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking Services","created":"2025-05-29","cited_by_count":2,"area":"mllm"},{"id":"2508.03079","title":"Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQA","created":"2025-08-05","cited_by_count":2,"area":"mllm"},{"id":"2506.16724","title":"The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models","created":"2025-06-20","cited_by_count":1,"area":"mllm"},{"id":"2511.13005","title":"SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal Bias","created":"2025-11-17","cited_by_count":1,"area":"mllm"},{"id":"2412.04939","title":"Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models","created":"2024-12-06","cited_by_count":0,"area":"mllm"},{"id":"2606.05874","title":"Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models","created":"2026-06-04","cited_by_count":0,"area":"mllm"},{"id":"2607.18673","title":"MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2608.29996","title":"Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models","created":"2026-08-30","cited_by_count":0,"area":"mllm"},{"id":"2608.30712","title":"GUIDE: Guiding Internal Evidence with Language Instructions","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.18345","title":"Visual Input and Its Framing Affect Attribute-based Descriptions Produced by Large Vision-Language Models","created":"2026-09-16","cited_by_count":0,"area":"mllm"}],"next_cursor":null}