Cover Image

When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Zolfaghari, Vahideh
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PediatricAnxietyBench: Evaluating Large Language Model Safety Under Parental Anxiety and Pressure in Pediatric Consultations
by: Zolfaghari, Vahideh
Published: (2025)

Cross-Platform Evaluation of Large Language Model Safety in Pediatric Consultations: Evolution of Adversarial Robustness and the Scale Paradox
by: Zolfaghari, Vahideh
Published: (2025)

When Truthful Representations Flip Under Deceptive Instructions?
by: Long, Xianxuan, et al.
Published: (2025)

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
by: Wang, Kai, et al.
Published: (2025)

FedBWO: Enhancing Communication Efficiency in Federated Learning
by: Hayyolalam, Vahideh, et al.
Published: (2025)

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
by: Fernández-Hernández, Alberto, et al.
Published: (2026)

Stable but Wrong: When More Data Degrades Scientific Conclusions
by: Zhang, Zhipeng, et al.
Published: (2026)

Exploiting Latent Linearity in LLMs Improves Explainable Molecular Representation Learning
by: Li, Zhuoran, et al.
Published: (2024)

Easy Problems That LLMs Get Wrong
by: Williams, Sean, et al.
Published: (2024)

Deceptive Exploration in Multi-armed Bandits
by: Vurankaya, I. Arda, et al.
Published: (2025)

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
by: Williams, Marcus, et al.
Published: (2024)

All AI Models are Wrong, but Some are Optimal
by: Anand, Akhil S, et al.
Published: (2025)

Automating Deception: Scalable Multi-Turn LLM Jailbreaks
by: Kumarappan, Adarsh, et al.
Published: (2025)

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
by: Kumar, Sachin
Published: (2026)

IoMT-based Automated Leukemia Classification using CNN and Higher Order Singular Value
by: Marzijarani, Shabnam Bagheri, et al.
Published: (2025)

When Can LLMs Learn to Reason with Weak Supervision?
by: Rahman, Salman, et al.
Published: (2026)

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
by: Chaudhary, Maheep, et al.
Published: (2025)

Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning
by: Liu, Xin, et al.
Published: (2024)

Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTL
by: Cai, Siyang, et al.
Published: (2026)

WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records
by: Dong, Ruan, et al.
Published: (2026)

When Privacy Isn't Synthetic: Hidden Data Leakage in Generative AI Models
by: Mustaqim, S. M., et al.
Published: (2025)

Multi-task Representation Learning for Mixed Integer Linear Programming
by: Cai, Junyang, et al.
Published: (2024)

Towards Effective Theory of LLMs: A Representation Learning Approach
by: Ustaomeroglu, Muhammed, et al.
Published: (2026)

A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
by: Omidvar, Hamed, et al.
Published: (2026)

DecepChain: Inducing Deceptive Reasoning in Large Language Models
by: Shen, Wei, et al.
Published: (2025)

Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation
by: Sikder, Md Fahim, et al.
Published: (2024)

CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter
by: Weng, Yepeng, et al.
Published: (2025)

Learning Distinguishable Representations in Deep Q-Networks for Linear Transfer
by: Sathish, Sooraj, et al.
Published: (2025)

Generative Modeling of Class Probability for Multi-Modal Representation Learning
by: Shin, Jungkyoo, et al.
Published: (2025)

Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL
by: Abdulhai, Marwa, et al.
Published: (2025)

any4: Learned 4-bit Numeric Representation for LLMs
by: Elhoushi, Mostafa, et al.
Published: (2025)

Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts
by: Khanh, Truong Xuan, et al.
Published: (2026)

Learning Cross-Atlas Consistent Brain Disorder Representations via Disentangled Multi-Atlas Functional Connectivity Learning
by: Chen, Minheng, et al.
Published: (2026)

Information-theoretic Distinctions Between Deception and Confusion
by: Young, Robin
Published: (2025)

A Multi-Task Learning Approach to Linear Multivariate Forecasting
by: Nochumsohn, Liran, et al.
Published: (2025)

Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
by: Li, Zhe, et al.
Published: (2025)

Among Us: A Sandbox for Measuring and Detecting Agentic Deception
by: Golechha, Satvik, et al.
Published: (2025)

Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series
by: Vapsi, Annita, et al.
Published: (2026)

Thinking Wrong in Silence: Backdoor Attacks on Continuous Latent Reasoning
by: Parekh, Swapnil
Published: (2026)

When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
by: Zhang, Nan, et al.
Published: (2025)