Cover Image

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Karnik, Sathwik, Bansal, Somil
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

Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
by: Karnik, Sathwik, et al.
Published: (2026)

Verification of Neural Reachable Tubes via Scenario Optimization and Conformal Prediction
by: Lin, Albert, et al.
Published: (2023)

Discovering Closed-Loop Failures of Vision-Based Controllers via Reachability Analysis
by: Chakraborty, Kaustav, et al.
Published: (2022)

Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks
by: Wang, Hao, et al.
Published: (2025)

An Efficient Reachability-Based Framework for Provably Safe Autonomous Navigation in Unknown Environments
by: Bajcsy, Andrea, et al.
Published: (2019)

Steer LLM Latents for Hallucination Detection
by: Park, Seongheon, et al.
Published: (2025)

One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments
by: Lin, Albert, et al.
Published: (2024)

LLM Misalignment via Adversarial RLHF Platforms
by: Entezami, Erfan, et al.
Published: (2025)

Preemptive Detection and Correction of Misaligned Actions in LLM Agents
by: Fang, Haishuo, et al.
Published: (2024)

BarrierSteer: LLM Safety via Learning Barrier Steering
by: Tran, Thanh Q., et al.
Published: (2026)

Robust Verification of Controllers under State Uncertainty via Hamilton-Jacobi Reachability Analysis
by: Lin, Albert, et al.
Published: (2025)

Multi-Attribute Steering of Language Models via Targeted Intervention
by: Nguyen, Duy, et al.
Published: (2025)

Embodied Red Teaming for Auditing Robotic Foundation Models
by: Karnik, Sathwik, et al.
Published: (2024)

Steered LLM Activations are Non-Surjective
by: Mishra, Aayush, et al.
Published: (2026)

Overtrained, Not Misaligned
by: Schreiber, Joel, et al.
Published: (2026)

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization
by: Egbuna, Nathan, et al.
Published: (2025)

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
by: Liu, Andy Zeyi, et al.
Published: (2026)

Understanding Emergent Misalignment via Feature Superposition Geometry
by: Minegishi, Gouki, et al.
Published: (2026)

Steer Like the LLM: Activation Steering that Mimics Prompting
by: Heyman, Geert, et al.
Published: (2026)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
by: Wang, Yiqi, et al.
Published: (2025)

BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking
by: Ustaomeroglu, Muhammed, et al.
Published: (2026)

Causal Identification in Time Series Models
by: Jahn, Erik, et al.
Published: (2025)

The Rogue Scalpel: Activation Steering Compromises LLM Safety
by: Korznikov, Anton, et al.
Published: (2025)

Steering LLM Reasoning Through Bias-Only Adaptation
by: Sinii, Viacheslav, et al.
Published: (2025)

Graph-Regularized Sparse Autoencoders for LLM Safety Steering
by: Yeon, Jehyeok, et al.
Published: (2025)

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

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
by: Xiao, Hanqi, et al.
Published: (2026)

Model Organisms for Emergent Misalignment
by: Turner, Edward, et al.
Published: (2025)

KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits
by: Ran, Dezhi, et al.
Published: (2025)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
by: Jiang, Xinyan, et al.
Published: (2026)

Convergent Linear Representations of Emergent Misalignment
by: Soligo, Anna, et al.
Published: (2025)

Misalignment from Treating Means as Ends
by: Marklund, Henrik, et al.
Published: (2025)

Benchmarking Suite for Synthetic Aperture Radar Imagery Anomaly Detection (SARIAD) Algorithms
by: Chauvin, Lucian, et al.
Published: (2025)

Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement
by: Wang, Anyi, et al.
Published: (2025)

Steering LLMs via Scalable Interactive Oversight
by: Zhou, Enyu, et al.
Published: (2026)

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
by: Zhou, Yefan, et al.
Published: (2026)

Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models
by: Ramjee, Sharan
Published: (2026)

Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework
by: Tiwari, Aman, et al.
Published: (2024)

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

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