Cover Image

Can LLMs Introspect? A Reality Check

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Singh, Shashwat, Linzen, Tal, Ravfogel, Shauli
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

State over Tokens: Characterizing the Role of Reasoning Tokens
by: Levy, Mosh, et al.
Published: (2025)

Emergence of Linear Truth Encodings in Language Models
by: Ravfogel, Shauli, et al.
Published: (2025)

Gumbel Counterfactual Generation From Language Models
by: Ravfogel, Shauli, et al.
Published: (2024)

Intrinsic Test of Unlearning Using Parametric Knowledge Traces
by: Hong, Yihuai, et al.
Published: (2024)

Evaluating In-Context Translation with Synchronous Context-Free Grammar Transduction
by: Petty, Jackson, et al.
Published: (2026)

RELIC: Evaluating Complex Reasoning via the Recognition of Languages In-Context
by: Petty, Jackson, et al.
Published: (2025)

Detecting the Disturbance: A Nuanced View of Introspective Abilities in LLMs
by: Hahami, Ely, et al.
Published: (2025)

Introspection Adapters: Training LLMs to Report Their Learned Behaviors
by: Shenoy, Keshav, et al.
Published: (2026)

Language Models Struggle to Use Representations Learned In-Context
by: Lepori, Michael A., et al.
Published: (2026)

Rapid Word Learning Through Meta In-Context Learning
by: Wang, Wentao, et al.
Published: (2025)

Can LLMs Automate Fact-Checking Article Writing?
by: Sahnan, Dhruv, et al.
Published: (2025)

Latent Introspection: Models Can Detect Prior Concept Injections
by: Pearson-Vogel, Theia, et al.
Published: (2026)

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
by: Li, Jiaqi, et al.
Published: (2025)

Looking Inward: Language Models Can Learn About Themselves by Introspection
by: Binder, Felix J, et al.
Published: (2024)

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

Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time
by: Hu, Michael Y., et al.
Published: (2026)

Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
by: Hu, Michael Y., et al.
Published: (2025)

Representation Surgery: Theory and Practice of Affine Steering
by: Singh, Shashwat, et al.
Published: (2024)

SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio
by: Pandey, Satwik, et al.
Published: (2026)

Introspection of Thought Helps AI Agents
by: Sun, Haoran, et al.
Published: (2025)

Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
by: Qiu, Linlu, et al.
Published: (2025)

Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild
by: Yao, Shanle, et al.
Published: (2026)

A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models
by: Eisape, Tiwalayo, et al.
Published: (2023)

A Reality Check on Context Utilisation for Retrieval-Augmented Generation
by: Hagström, Lovisa, et al.
Published: (2024)

MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents
by: Tang, Liyan, et al.
Published: (2024)

Me, Myself, and $π$ : Evaluating and Explaining LLM Introspection
by: Naphade, Atharv, et al.
Published: (2026)

Can LLMs Capture Human Preferences?
by: Goli, Ali, et al.
Published: (2023)

Emergent Introspection in AI is Content-Agnostic
by: Lederman, Harvey, et al.
Published: (2026)

Deep Active Learning: A Reality Check
by: Gashi, Edrina, et al.
Published: (2024)

InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
by: Bai, Yuzhuo, et al.
Published: (2026)

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
by: Sinha, Akshit, et al.
Published: (2025)

Emergent Introspective Awareness in Large Language Models
by: Lindsey, Jack
Published: (2026)

Privileged Self-Access Matters for Introspection in AI
by: Song, Siyuan, et al.
Published: (2025)

Exploration Through Introspection: A Self-Aware Reward Model
by: Petrowski, Michael, et al.
Published: (2026)

Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation
by: Martorell, Nicolas, et al.
Published: (2026)

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

Preserving Task-Relevant Information Under Linear Concept Removal
by: Holstege, Floris, et al.
Published: (2025)

Log-linear Guardedness and its Implications
by: Ravfogel, Shauli, et al.
Published: (2022)

How LLMs Fail to Support Fact-Checking
by: Proma, Adiba Mahbub, et al.
Published: (2025)

Behavioral Cloning Models Reality Check for Autonomous Driving
by: Yildirim, Mustafa, et al.
Published: (2024)