Cover Image

Looking Inward: Language Models Can Learn About Themselves by Introspection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Binder, Felix J, Chua, James, Korbak, Tomek, Sleight, Henry, Hughes, John, Long, Robert, Perez, Ethan, Turpin, Miles, Evans, Owain
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Lessons from Studying Two-Hop Latent Reasoning
by: Balesni, Mikita, et al.
Published: (2024)

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

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

Can Language Models Explain Their Own Classification Behavior?
by: Sherburn, Dane, et al.
Published: (2024)

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

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

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
by: Chua, James, et al.
Published: (2024)

Training Agents to Self-Report Misbehavior
by: Lee, Bruce W., et al.
Published: (2026)

How to evaluate control measures for LLM agents? A trajectory from today to superintelligence
by: Korbak, Tomek, et al.
Published: (2025)

Language Models Fail to Introspect About Their Knowledge of Language
by: Song, Siyuan, et al.
Published: (2025)

Safety Cases: A Scalable Approach to Frontier AI Safety
by: Hilton, Benjamin, et al.
Published: (2025)

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

A sketch of an AI control safety case
by: Korbak, Tomek, et al.
Published: (2025)

Rapid Response: Mitigating LLM Jailbreaks with a Few Examples
by: Peng, Alwin, et al.
Published: (2024)

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
by: Schaeffer, Rylan, et al.
Published: (2024)

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

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

Look Inward before Looking Outward: Preparing the School Library Media Center for Cooperative Collection Development.
by: Kachel, Debra E.
Published: (1995)

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models
by: Ensign, Danielle, et al.
Published: (2025)

Transfer, Lead, Look Inward: Further Study of Preservice School Librarians' Development
by: Mardis, Marcia A.
Published: (2013)

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

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

Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
by: Youstra, Jack, et al.
Published: (2025)

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
by: Hägele, Alexander, et al.
Published: (2026)

Can LLMs Explain Themselves Counterfactually?
by: Dehghanighobadi, Zahra, et al.
Published: (2025)

Looking Inwards: The Role of Self‐Care, Self‐Management and Self‐Healing in Musculoskeletal Pain
by: Joyce McSwan, et al.
Published: (2025)

Best-of-N Jailbreaking
by: Hughes, John, et al.
Published: (2024)

Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach
by: Wang, Tony T., et al.
Published: (2024)

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

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
by: Davies, Xander, et al.
Published: (2025)

Introspective Diffusion Language Models
by: Yu, Yifan, et al.
Published: (2026)

Practical challenges of control monitoring in frontier AI deployments
by: Lindner, David, et al.
Published: (2025)

Decolonization and the Inward Journey
by: Carlton Turner
Published: (2025)

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

From Normal to Disaster Response Mode: How Can Virtual Communities Reconfigure Themselves to Respond Effectively to a Disaster?
by: Mahmudul Hasan, et al.
Published: (2025)

Can LLMs Introspect? A Reality Check
by: Singh, Shashwat, et al.
Published: (2026)

Stress-Testing Model Specs Reveals Character Differences among Language Models
by: Zhang, Jifan, et al.
Published: (2025)

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

Safety case template for frontier AI: A cyber inability argument
by: Goemans, Arthur, et al.
Published: (2024)

Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?
by: Liao, Yuan-Hong, et al.
Published: (2024)