Cover Image

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chua, James, Betley, Jan, Taylor, Mia, Evans, Owain
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
by: Betley, Jan, et al.
Published: (2025)

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
by: Betley, Jan, et al.
Published: (2025)

The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
by: Chua, James, et al.
Published: (2026)

Tell me about yourself: LLMs are aware of their learned behaviors
by: Betley, Jan, et al.
Published: (2025)

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
by: Treutlein, Johannes, et al.
Published: (2024)

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
by: Taylor, Mia, et al.
Published: (2025)

Negation Neglect: When models fail to learn negations in training
by: Mayne, Harry, et al.
Published: (2026)

Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
by: Cloud, Alex, et al.
Published: (2025)

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
by: Laine, Rudolf, et al.
Published: (2024)

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

Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers
by: Dubiński, Jan, et al.
Published: (2026)

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

Persona-Model Collapse in Emergent Misalignment
by: Costa, Davi Bastos, et al.
Published: (2026)

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
by: Askin, Baris, et al.
Published: (2026)

The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs
by: Dickson, Craig
Published: (2025)

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
by: Giordani, Jeremiah
Published: (2025)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
by: Ye, Jiacheng, et al.
Published: (2024)

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
by: Karvonen, Adam, et al.
Published: (2025)

Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
by: Chan, Yik Siu, et al.
Published: (2025)

Enhancing Generalization in Chain of Thought Reasoning for Smaller Models
by: Yin, Maxwell J., et al.
Published: (2025)

Fractured Chain-of-Thought Reasoning
by: Liao, Baohao, et al.
Published: (2025)

ORION: Teaching Language Models to Reason Efficiently in the Language of Thought
by: Tanmay, Kumar, et al.
Published: (2025)

Toward Adaptive Reasoning in Large Language Models with Thought Rollback
by: Chen, Sijia, et al.
Published: (2024)

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
by: Boppana, Siddharth, et al.
Published: (2026)

Synergy-of-Thoughts: Eliciting Efficient Reasoning in Hybrid Language Models
by: Shang, Yu, et al.
Published: (2024)

Reasoning to Learn from Latent Thoughts
by: Ruan, Yangjun, et al.
Published: (2025)

$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models
by: Cai, Chengkun, et al.
Published: (2024)

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
by: Berglund, Lukas, et al.
Published: (2023)

Epistemic Traps: Rational Misalignment Driven by Model Misspecification
by: Xu, Xingcheng, et al.
Published: (2026)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

Reasoning with Latent Thoughts: On the Power of Looped Transformers
by: Saunshi, Nikunj, et al.
Published: (2025)

Compositional Reasoning with Transformers, RNNs, and Chain of Thought
by: Yehudai, Gilad, et al.
Published: (2025)

Scalable Chain of Thoughts via Elastic Reasoning
by: Xu, Yuhui, et al.
Published: (2025)

Long Chain-of-Thought Reasoning Across Languages
by: Barua, Josh, et al.
Published: (2025)

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
by: Yang, Ling, et al.
Published: (2025)

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
by: Guo, Shiyuan, et al.
Published: (2025)

Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning
by: Yue, Murong, et al.
Published: (2023)

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
by: Chen, Changyu, et al.
Published: (2024)

Are DeepSeek R1 And Other Reasoning Models More Faithful?
by: Chua, James, et al.
Published: (2025)

Weight-of-Thought Reasoning: Exploring Neural Network Weights for Enhanced LLM Reasoning
by: Punjwani, Saif, et al.
Published: (2025)