# HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs

arXiv: https://arxiv.org/abs/2506.13038 · HTML: https://mlsanity.com/paper/2506.13038/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)
- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2310.05338/) (2023)
- [EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning](https://mlsanity.com/paper/2210.07795/) (2022)
- [A Review of Multi-Modal Large Language and Vision Models](https://mlsanity.com/paper/2404.01322/) (2024)
- [Synergizing RAG and Reasoning: A Systematic Review](https://mlsanity.com/paper/2504.15909/) (2025)
- [TI-CNN: Convolutional Neural Networks for Fake News Detection](https://mlsanity.com/paper/1806.00749/) (2018)
- [Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies](https://mlsanity.com/paper/2412.05155/) (2024)
- [A Deep Learning Approach for Automatic Detection of Fake News](https://mlsanity.com/paper/2005.04938/) (2020)
- [VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition](https://mlsanity.com/paper/2408.16930/) (2024)
- [Detect, Investigate, Judge and Determine: A Knowledge-guided Framework for Few-shot Fake News Detection](https://mlsanity.com/paper/2407.08952/) (2024)
- [Towards Emotion Analysis in Short-form Videos: A Large-Scale Dataset and Baseline](https://mlsanity.com/paper/2311.17335/) (2023)
- [TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs](https://mlsanity.com/paper/2504.07556/) (2025)

## Built on by (most cited first, 3 of 3)

- [ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model](https://mlsanity.com/paper/2510.24285/) (2025)
- [MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook](https://mlsanity.com/paper/2509.14142/) (2025)
- [AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning](https://mlsanity.com/paper/2604.17889/) (2026)

## Abstract (arXiv)

Driven by the rapid progress in vision-language models (VLMs), the responsible behavior of large-scale multimodal models has become a prominent research area, particularly focusing on hallucination detection and factuality checking. In this paper, we present the solution for the two tracks of Responsible AI challenge. Inspirations from the general domain demonstrate that a smaller distilled VLM can often outperform a larger VLM that is directly tuned on downstream tasks, while achieving higher efficiency. We thus jointly tackle two tasks from the perspective of knowledge distillation and propose a progressive hybrid knowledge distillation framework termed HKD4VLM. Specifically, the overall framework can be decomposed into Pyramid-like Progressive Online Distillation and Ternary-Coupled Refinement Distillation, hierarchically moving from coarse-grained knowledge alignment to fine-grained refinement. Besides, we further introduce the mapping shift-enhanced inference and diverse augmentation strategies to enhance model performance and robustness. Extensive experimental results demonstrate the effectiveness of our HKD4VLM. Ablation studies provide insights into the critical design choices driving performance gains.