# EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2402.09801 · HTML: https://mlsanity.com/paper/2402.09801/

## Key facts

- Cited by 17 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 17 of its 37 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization](https://mlsanity.com/paper/2311.16839/) (2023)
- [Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision](https://mlsanity.com/paper/2311.07362/) (2023)
- [VIGC: Visual Instruction Generation and Correction](https://mlsanity.com/paper/2308.12714/) (2023)

## Built on by (most cited first, 17 of 17)

- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Machine Unlearning in Generative AI: A Survey](https://mlsanity.com/paper/2407.20516/) (2024)
- [Mitigating Object Hallucinations via Sentence-Level Early Intervention](https://mlsanity.com/paper/2507.12455/) (2025)
- [VidHal: Benchmarking Temporal Hallucinations in Vision LLMs](https://mlsanity.com/paper/2411.16771/) (2024)
- [MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification](https://mlsanity.com/paper/2405.19186/) (2024)
- [MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering](https://mlsanity.com/paper/2510.04217/) (2025)
- [A Mechanistic View of Authority Hierarchy in LLM Sycophancy](https://mlsanity.com/paper/2607.00415/) (2026)
- [Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations](https://mlsanity.com/paper/2410.15359/) (2024)
- [A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions](https://mlsanity.com/paper/2412.12836/) (2024)
- [Multi-Objective Large Language Model Unlearning](https://mlsanity.com/paper/2412.20412/) (2024)
- [Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2601.22020/) (2026)
- [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025)
- [Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection](https://mlsanity.com/paper/2509.03113/) (2025)
- [ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2605.05938/) (2026)
- [LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning](https://mlsanity.com/paper/2605.01047/) (2026)
- [Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs](https://mlsanity.com/paper/2606.28401/) (2026)
- [CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation](https://mlsanity.com/paper/2610.14763/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon known as object hallucination. To eliminate hallucinations, existing methods manually annotate paired responses with and without hallucinations, and then employ various alignment algorithms to improve the alignment capability between images and text. However, they not only demand considerable computation resources during the finetuning stage but also require expensive human annotation to construct paired data needed by the alignment algorithms. To address these issues, we borrow the idea of unlearning and propose an efficient fine-grained unlearning framework (EFUF), which can eliminate hallucinations without the need for paired data. Extensive experiments show that our method consistently reduces hallucinations while preserving the generation quality with modest computational overhead. Our code and datasets will be publicly available.