Cover Image

MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Lili, Liu, Qi, Chen, Wei, Chen, Liyi, Sun, Ruijun, Hou, Min, Wang, Yang, Wang, Shijin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Revealing and Mitigating the Local Pattern Shortcuts of Mamba
by: You, Wangjie, et al.
Published: (2024)

A Typology for Exploring the Mitigation of Shortcut Behavior
by: Friedrich, Felix, et al.
Published: (2022)

Mitigating Shortcut Learning with InterpoLated Learning
by: Korakakis, Michalis, et al.
Published: (2025)

From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis
by: Li, Kecen, et al.
Published: (2025)

Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach
by: Cao, Hongyu, et al.
Published: (2026)

Rectifying Shortcut Behaviors in Preference-based Reward Learning
by: Ye, Wenqian, et al.
Published: (2025)

Demystifying MuZero Planning: Interpreting the Learned Model
by: Guei, Hung, et al.
Published: (2024)

Learning with Logical Constraints but without Shortcut Satisfaction
by: Li, Zenan, et al.
Published: (2024)

BackMix: Mitigating Shortcut Learning in Echocardiography with Minimal Supervision
by: Bransby, Kit Mills, et al.
Published: (2024)

Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
by: Yue, Linan, et al.
Published: (2024)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
by: Scimeca, Luca, et al.
Published: (2023)

Simulating Human-Like Learning Dynamics with LLM-Empowered Agents
by: Yuan, Yu, et al.
Published: (2025)

Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process
by: Xiao, Tong, et al.
Published: (2024)

Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding
by: Chi, Ziheng, et al.
Published: (2025)

Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
by: Kwon, JuneHyoung, et al.
Published: (2024)

A Survey of Models for Cognitive Diagnosis: New Developments and Future Directions
by: Wang, Fei, et al.
Published: (2024)

Latent Shadows: The Gaussian-Discrete Duality in Masked Diffusion
by: Chen, Guinan, et al.
Published: (2026)

Unified Uncertainty Estimation for Cognitive Diagnosis Models
by: Wang, Fei, et al.
Published: (2024)

STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering
by: Chen, Wei, et al.
Published: (2026)

On the Shortcut Learning in Multilingual Neural Machine Translation
by: Wang, Wenxuan, et al.
Published: (2024)

Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models
by: Sakib, Fardin Ahsan, et al.
Published: (2025)

Shortcut to Nowhere: Demystifying Deep Spurious Regression
by: Xu, Guanrong, et al.
Published: (2026)

MuPT: A Generative Symbolic Music Pretrained Transformer
by: Qu, Xingwei, et al.
Published: (2024)

CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
by: Liu, Jiayu, et al.
Published: (2025)

P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer
by: Wang, Zhiyuan, et al.
Published: (2024)

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning
by: Chen, Liuji, et al.
Published: (2026)

Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models
by: Cui, Yiming, et al.
Published: (2021)

DeMuVGN: Effective Software Defect Prediction Model by Learning Multi-view Software Dependency via Graph Neural Networks
by: Qiao, Yu, et al.
Published: (2024)

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
by: Liu, Qin, et al.
Published: (2023)

When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents
by: Sheng, Strick, et al.
Published: (2026)

A Transformer-Based Conditional GAN with Multiple Instance Learning for UAV Signal Detection and Classification
by: Liu, Haochen, et al.
Published: (2025)

Behavior Backdoor for Deep Learning Models
by: Wang, Jiakai, et al.
Published: (2024)

MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents
by: Zhao, Pengxiang, et al.
Published: (2025)

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
by: Steinmann, David, et al.
Published: (2024)

CursorCore: Assist Programming through Aligning Anything
by: Jiang, Hao, et al.
Published: (2024)

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
by: Wang, Xiangmeng, et al.
Published: (2026)

MuLMINet: Multi-Layer Multi-Input Transformer Network with Weighted Loss
by: Seong, Minwoo, et al.
Published: (2023)

Constraint-Based Analysis of Reasoning Shortcuts in Neurosymbolic Learning
by: Takemura, Akihiro, et al.
Published: (2026)

Shortcut Learning in In-Context Learning: A Survey
by: Song, Rui, et al.
Published: (2024)

Rectifying Demonstration Shortcut in In-Context Learning
by: Jang, Joonwon, et al.
Published: (2024)