Cover Image

Revealing and Mitigating the Local Pattern Shortcuts of Mamba

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	You, Wangjie, Tang, Zecheng, Li, Juntao, Yao, Lili, Zhang, Min
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Revealing and Mitigating Over-Attention in Knowledge Editing
by: Wang, Pinzheng, et al.
Published: (2025)

LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling
by: Tang, Zecheng, et al.
Published: (2025)

Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective
by: You, Wangjie, et al.
Published: (2025)

MemLong: Memory-Augmented Retrieval for Long Text Modeling
by: Liu, Weijie, et al.
Published: (2024)

LOGO -- Long cOntext aliGnment via efficient preference Optimization
by: Tang, Zecheng, et al.
Published: (2024)

Revisiting Long-context Modeling from Context Denoising Perspective
by: Tang, Zecheng, et al.
Published: (2025)

MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
by: Ji, Baibei, et al.
Published: (2026)

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models
by: Tang, Zecheng, et al.
Published: (2026)

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
by: Tang, Zecheng, et al.
Published: (2026)

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

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

Unlocking Recursive Thinking of LLMs: Alignment via Refinement
by: Zhang, Haoke, et al.
Published: (2025)

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

RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns
by: Chen, Xin, et al.
Published: (2025)

Break the Chain: Large Language Models Can be Shortcut Reasoners
by: Ding, Mengru, et al.
Published: (2024)

CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
by: Kocak, Aysenur, et al.
Published: (2025)

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

Fennec: Fine-grained Language Model Evaluation and Correction Extended through Branching and Bridging
by: Liang, Xiaobo, et al.
Published: (2024)

Multi-Persona Thinking for Bias Mitigation in Large Language Models
by: Chen, Yuxing, et al.
Published: (2026)

Navigation with VLM framework: Towards Going to Any Language
by: Yin, Zecheng, et al.
Published: (2024)

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

Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation
by: Luo, Guoqing, et al.
Published: (2025)

Bi-Mamba: Towards Accurate 1-Bit State Space Models
by: Tang, Shengkun, et al.
Published: (2024)

Timo: Towards Better Temporal Reasoning for Language Models
by: Su, Zhaochen, et al.
Published: (2024)

MemMamba: Rethinking Memory Patterns in State Space Model
by: Wang, Youjin, et al.
Published: (2025)

Revealing the Role of Audio Channels in ASR Performance Degradation
by: Huang, Kuan-Tang, et al.
Published: (2025)

The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
by: Kim, Dueun, et al.
Published: (2026)

Mitigating the Negative Impact of Over-association for Conversational Query Production
by: Wang, Ante, et al.
Published: (2024)

Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?
by: Li, Bangzheng, et al.
Published: (2023)

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch
by: Ding, Yuyang, et al.
Published: (2024)

Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models
by: Mikula, Lukáš, et al.
Published: (2023)

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
by: Su, Zhaochen, et al.
Published: (2024)

Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities
by: Lehmann, Hans Hergen, et al.
Published: (2025)

Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs
by: Zi, Xing, et al.
Published: (2026)

Mitigating Gender Bias in Code Large Language Models via Model Editing
by: Qin, Zhanyue, et al.
Published: (2024)

Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
by: Zhang, Hongbin, et al.
Published: (2024)

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
by: Zhou, Yigeng, et al.
Published: (2026)

The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts
by: Madhusudan, Sangmitra, et al.
Published: (2025)

ChatPattern: Layout Pattern Customization via Natural Language
by: Wang, Zixiao, et al.
Published: (2024)