{"total":18,"rows":[{"id":"2501.02189","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","created":"2025-01-04","cited_by_count":47,"area":"mllm"},{"id":"2505.01481","title":"VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding","created":"2025-05-02","cited_by_count":32,"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":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"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":"2409.13612","title":"FIHA: Autonomous Hallucination Evaluation in Vision-Language Models with Davidson Scene Graphs","created":"2024-09-20","cited_by_count":3,"area":"mllm"},{"id":"2505.24007","title":"Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Model","created":"2025-05-29","cited_by_count":2,"area":"mllm"},{"id":"2508.10955","title":"Empowering Multimodal LLMs with External Tools: A Comprehensive Survey","created":"2025-08-14","cited_by_count":2,"area":"mllm"},{"id":"2509.13836","title":"Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models","created":"2025-09-17","cited_by_count":1,"area":"mllm"},{"id":"2509.20379","title":"Leveraging NTPs for Efficient Hallucination Detection in VLMs","created":"2025-09-20","cited_by_count":1,"area":"mllm"},{"id":"2510.19892","title":"Can They Dixit? Yes they Can! Dixit as a Playground for Multimodal Language Model Capabilities","created":"2025-10-22","cited_by_count":1,"area":"mllm"},{"id":"2605.30911","title":"What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness","created":"2026-05-29","cited_by_count":1,"area":"mllm"},{"id":"2608.07525","title":"Unified Hallucination Fuzzing for Multimodal Large Language Models","created":"2026-07-15","cited_by_count":1,"area":"mllm"},{"id":"2605.04641","title":"CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering","created":"2026-05-06","cited_by_count":0,"area":"mllm"},{"id":"2606.17953","title":"MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias","created":"2026-06-16","cited_by_count":0,"area":"mllm"},{"id":"2608.25662","title":"Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language Models","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2610.02878","title":"Evaluating VQA in Vision Language Models using Cooperative Principles","created":"2026-10-02","cited_by_count":0,"area":"mllm"},{"id":"2610.08106","title":"ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications","created":"2026-10-06","cited_by_count":0,"area":"mllm"}],"next_cursor":null}