MPI-CD: Multi-Path Information Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4251-4260
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (Grant No. 61977045)
This publication has 20 references indexed in Scilit:
- SkyEyeGPT: Unifying remote sensing vision-language tasks via instruction tuning with large language modelISPRS Journal of Photogrammetry and Remote Sensing, 2025
- Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs2024
- Improved Baselines with Visual Instruction Tuning2024
- OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation2024
- GLaMM: Pixel Grounding Large Multimodal Model2024
- From image to language: A critical analysis of Visual Question Answering (VQA) approaches, challenges, and opportunitiesInformation Fusion, 2024
- A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge2022
- GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering2019
- Visual perception and memory systems: from cortex to medial temporal lobeCellular and Molecular Life Sciences, 2011
- Human detection using a mobile platform and novel features derived from a visual saliency mechanismImage and Vision Computing, 2010