Cover Image

Mitigating Cognitive Inertia in Large Reasoning Models via Latent Spike Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Seojin, Kim, ByeongJeong, Lee, Hwanhee
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification
by: Park, Gyutae, et al.
Published: (2024)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
by: Huang, Yao, et al.
Published: (2025)

Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models
by: Park, Gyutae, et al.
Published: (2024)

Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors
by: Bao, Qiming, et al.
Published: (2025)

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
by: Wu, Jialin, et al.
Published: (2026)

Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation
by: Shin, Yehjin, et al.
Published: (2026)

Graph Structure Based Data Augmentation Method
by: Kim, Kyung Geun, et al.
Published: (2022)

Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
by: Jang, Suhyeok, et al.
Published: (2024)

Latent Policy Steering through One-Step Flow Policies
by: Im, Hokyun, et al.
Published: (2026)

Mitigating Conversational Inertia in Multi-Turn Agents
by: Wan, Yang, et al.
Published: (2026)

Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
by: Li, Yawei, et al.
Published: (2026)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
by: Zhang, Zhenyu, et al.
Published: (2025)

CBMAS: Cognitive Behavioral Modeling via Activation Steering
by: Ismail, Ahmed H., et al.
Published: (2026)

Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization
by: Jhin, Sheo Yon, et al.
Published: (2024)

Enhancing Multilingual RAG Systems with Debiased Language Preference-Guided Query Fusion
by: Park, Jeonghyun, et al.
Published: (2026)

TARDIS: Mitigating Temporal Misalignment via Representation Steering
by: Shin, Changho, et al.
Published: (2025)

Multi-View Node Pruning for Accurate Graph Representation
by: Kim, Hanjin, et al.
Published: (2025)

Personality Editing for Language Models through Adjusting Self-Referential Queries
by: Hwang, Seojin, et al.
Published: (2025)

Unveiling the Latent Directions of Reflection in Large Language Models
by: Chang, Fu-Chieh, et al.
Published: (2025)

Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment
by: Hwang, Seojin, et al.
Published: (2026)

Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
by: Yang, Jiaxi, et al.
Published: (2026)

Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute
by: Liu, Sheng, et al.
Published: (2025)

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment
by: Gadgil, Soham, et al.
Published: (2026)

Semi-Supervised Preference Optimization with Limited Feedback
by: Lee, Seonggyun, et al.
Published: (2025)

Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs
by: Yang, Jaewoo, et al.
Published: (2024)

Understanding Reasoning in Thinking Language Models via Steering Vectors
by: Venhoff, Constantin, et al.
Published: (2025)

Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
by: Son, Seungwoo, et al.
Published: (2024)

Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)
by: Lee, Yousung, et al.
Published: (2026)

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
by: Hahm, Jaehoon, et al.
Published: (2024)

Learning to Control Camera Exposure via Reinforcement Learning
by: Lee, Kyunghyun, et al.
Published: (2024)

Mitigating Hallucinations in Large Language Models via Causal Reasoning
by: Li, Yuangang, et al.
Published: (2025)

LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
by: Lee, Banseok, et al.
Published: (2026)

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
by: Karnik, Sathwik, et al.
Published: (2025)

DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
by: Park, Dogyun, et al.
Published: (2024)

ATLAS: Adaptive Test-Time Latent Steering with External Verifiers for Enhancing LLMs Reasoning
by: Nguyen, Tuc, et al.
Published: (2026)

Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning
by: Wan, Qian, et al.
Published: (2026)

Towards Scalable Handwriting Communication via EEG Decoding and Latent Embedding Integration
by: Kim, Jun-Young, et al.
Published: (2024)

New Test-Time Scenario for Biosignal: Concept and Its Approach
by: Jo, Yong-Yeon, et al.
Published: (2024)

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning
by: Lee, Dohyeok, et al.
Published: (2024)

On Theoretical Identifiability of Discrete Latent Causal Graphical Models
by: Lee, Seunghyun, et al.
Published: (2025)