Cover Image

The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chua, James, Betley, Jan, Marks, Samuel, Evans, Owain
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
by: Chua, James, et al.
Published: (2025)

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

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
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)

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

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

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

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

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

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

Could a Large Language Model be Conscious?
by: Chalmers, David J.
Published: (2023)

From Imitation to Introspection: Probing Self-Consciousness in Language Models
by: Chen, Sirui, et al.
Published: (2024)

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

Persona Vectors: Monitoring and Controlling Character Traits in Language Models
by: Chen, Runjin, et al.
Published: (2025)

AirGapAgent: Protecting Privacy-Conscious Conversational Agents
by: Bagdasarian, Eugene, et al.
Published: (2024)

Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks
by: Chen, Sirui, et al.
Published: (2025)

OnPrem.LLM: A Privacy-Conscious Document Intelligence Toolkit
by: Maiya, Arun S.
Published: (2025)

Testing the Machine Consciousness Hypothesis
by: Fitz, Stephen
Published: (2025)

Erasing Conceptual Knowledge from Language Models
by: Gandikota, Rohit, et al.
Published: (2024)

Robustly Improving LLM Fairness in Realistic Settings via Interpretability
by: Karvonen, Adam, et al.
Published: (2025)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
by: Karvonen, Adam, 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)

Distill and Align Decomposition for Enhanced Claim Verification
by: Magomere, Jabez, et al.
Published: (2026)

ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs
by: Dammu, Preetam Prabhu Srikar, et al.
Published: (2024)

Emergent Abilities in Reduced-Scale Generative Language Models
by: Muckatira, Sherin, et al.
Published: (2024)

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

Aligning language models with human preferences
by: Korbak, Tomasz
Published: (2024)

Compositional preference models for aligning LMs
by: Go, Dongyoung, et al.
Published: (2023)

Emergent Stack Representations in Modeling Counter Languages Using Transformers
by: Tiwari, Utkarsh, et al.
Published: (2025)

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
by: Karvonen, Adam
Published: (2024)

LIRE: listwise reward enhancement for preference alignment
by: Zhu, Mingye, et al.
Published: (2024)

A density estimation perspective on learning from pairwise human preferences
by: Dumoulin, Vincent, et al.
Published: (2023)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
by: Marks, Samuel, et al.
Published: (2024)

Emergent Response Planning in LLMs
by: Dong, Zhichen, et al.
Published: (2025)

Predicting Emergent Capabilities by Finetuning
by: Snell, Charlie, et al.
Published: (2024)

FECT: Factuality Evaluation of Interpretive AI-Generated Claims in Contact Center Conversation Transcripts
by: Shin, Hagyeong, et al.
Published: (2025)

Inference time LLM alignment in single and multidomain preference spectrum
by: Shahriar, Sadat, et al.
Published: (2024)

Numerical Claim Detection in Finance: A New Financial Dataset, Weak-Supervision Model, and Market Analysis
by: Shah, Agam, et al.
Published: (2024)

Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment
by: Vaugrante, Laurène, et al.
Published: (2026)

The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models
by: Sawmya, Shashata, et al.
Published: (2025)