# PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2503.12545 · HTML: https://mlsanity.com/paper/2503.12545/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 38 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [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)
- [PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding](https://mlsanity.com/paper/2312.04461/) (2023)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [Continual Learning and Private Unlearning](https://mlsanity.com/paper/2203.12817/) (2022)
- [Machine Unlearning of Pre-trained Large Language Models](https://mlsanity.com/paper/2402.15159/) (2024)
- [Large Language Model Unlearning via Embedding-Corrupted Prompts](https://mlsanity.com/paper/2406.07933/) (2024)
- [Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs](https://mlsanity.com/paper/2111.13654/) (2021)
- [RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2406.10890/) (2024)
- [Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2405.12523/) (2024)

## Built on by (most cited first, 6 of 6)

- [OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models](https://mlsanity.com/paper/2510.22535/) (2025)
- [Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models](https://mlsanity.com/paper/2601.21794/) (2026)
- [Learning-Time Encoding Shapes Unlearning in LLMs](https://mlsanity.com/paper/2506.15076/) (2025)
- [ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2605.05938/) (2026)
- [PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models](https://mlsanity.com/paper/2605.08800/) (2026)
- [SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs](https://mlsanity.com/paper/2606.09868/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have achieved remarkable success in vision-language tasks, but their reliance on vast, internet-sourced data raises significant privacy and security concerns. Machine unlearning (MU) has emerged as a critical technique to address these issues, enabling the selective removal of targeted information from pre-trained models without costly retraining. However, the evaluation of MU for MLLMs remains inadequate. Existing benchmarks often lack a comprehensive scope, focusing narrowly on entities while overlooking the unlearning of broader visual concepts and the inherent semantic coupling between them. To bridge this gap, we introduce, PEBench, a novel benchmark designed to facilitate a thorough assessment of MU in MLLMs. PEBench features a fictitious dataset of personal entities and corresponding event scenes to evaluate unlearning across these distinct yet entangled concepts. We leverage this benchmark to evaluate five MU methods, revealing their unique strengths and weaknesses. Our findings show that unlearning one concept can unintentionally degrade performance on related concepts within the same image, a challenge we term cross-concept interference. Furthermore, we demonstrate the difficulty of unlearning person and event concepts simultaneously and propose an effective method to mitigate these conflicting objectives. The source code and benchmark are publicly available at https://pebench.github.io.