Cover Image

Toward Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Jiali, Chen, Ziheng, Agarwal, Chirag, Amiri, Hadi
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Understanding Machine Unlearning Through the Lens of Mode Connectivity
by: Cheng, Jiali, et al.
Published: (2025)

Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods
by: Cheng, Jiali, et al.
Published: (2025)

MultiDelete for Multimodal Machine Unlearning
by: Cheng, Jiali, et al.
Published: (2023)

Tool Unlearning for Tool-Augmented LLMs
by: Cheng, Jiali, et al.
Published: (2025)

CURE:Circuit-Aware Unlearning for LLM-based Recommendation
by: Chen, Ziheng, et al.
Published: (2026)

Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling
by: Li, Mingzhuo, et al.
Published: (2025)

Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View
by: Qi, Jianyu, et al.
Published: (2025)

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
by: Tian, Bozhong, et al.
Published: (2024)

Towards Reversible Model Merging For Low-rank Weights
by: Alipour, Mohammadsajad, et al.
Published: (2025)

Difficulty-aware Balancing Margin Loss for Long-tailed Recognition
by: Son, Minseok, et al.
Published: (2024)

On the Difficulty of Learning a Meta-network for Training Data Selection
by: Du, Zilin, et al.
Published: (2026)

Linguistic Blind Spots of Large Language Models
by: Cheng, Jiali, et al.
Published: (2025)

FairFlow: Mitigating Dataset Biases through Undecided Learning
by: Cheng, Jiali, et al.
Published: (2025)

Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models
by: Yang, Yongjin, et al.
Published: (2023)

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
by: Fang, Xianya, et al.
Published: (2026)

Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models
by: Seth, Ashish, et al.
Published: (2024)

$\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning
by: Trippa, Daniel, et al.
Published: (2024)

MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences
by: Winata, Genta Indra, et al.
Published: (2024)

Towards Understanding Camera Motions in Any Video
by: Lin, Zhiqiu, et al.
Published: (2025)

Beyond Pedestrians: Caption-Guided CLIP Framework for High-Difficulty Video-based Person Re-Identification
by: Hamano, Shogo, et al.
Published: (2026)

A Comparative Study of Machine Unlearning Techniques for Image and Text Classification Models
by: Safa, Omar M., et al.
Published: (2024)

Using Vision + Language Models to Predict Item Difficulty
by: Khan, Samin
Published: (2026)

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
by: Xu, Haoming, et al.
Published: (2025)

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
by: Ye, Jiabo, et al.
Published: (2024)

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
by: Ou, Yixin, et al.
Published: (2025)

Abstractive Visual Understanding of Multi-modal Structured Knowledge: A New Perspective for MLLM Evaluation
by: Zhang, Yichi, et al.
Published: (2025)

VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
by: Ku, Max, et al.
Published: (2023)

Transferring Textual Preferences to Vision-Language Understanding through Model Merging
by: Li, Chen-An, et al.
Published: (2025)

Deep Learning-Based Digitization of Overlapping ECG Images with Open-Source Python Code
by: Karbasi, Reza, et al.
Published: (2025)

TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation
by: Grimal, Paul, et al.
Published: (2023)

An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics
by: Ahmadi, Saba, et al.
Published: (2023)

VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety
by: Palaskar, Shruti, et al.
Published: (2025)

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
by: Patil, Vaidehi, et al.
Published: (2025)

Towards Human-Level Understanding of Complex Process Engineering Schematics: A Pedagogical, Introspective Multi-Agent Framework for Open-Domain Question Answering
by: Sakhinana, Sagar Srinivas, et al.
Published: (2024)

Hierarchy-Aware Multimodal Unlearning for Medical AI
by: Wu, Fengli, et al.
Published: (2025)

Examining the Commitments and Difficulties Inherent in Multimodal Foundation Models for Street View Imagery
by: Yang, Zhenyuan, et al.
Published: (2024)

ReLearn: Unlearning via Learning for Large Language Models
by: Xu, Haoming, et al.
Published: (2025)

A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty
by: Feng, Xiaohua, et al.
Published: (2025)

Physical Property Understanding from Language-Embedded Feature Fields
by: Zhai, Albert J., et al.
Published: (2024)

Towards the Resistance of Neural Network Watermarking to Fine-tuning
by: Tang, Ling, et al.
Published: (2025)