Copertina

Me, Myself, and $π$ : Evaluating and Explaining LLM Introspection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Naphade, Atharv, Bhargav, Samarth, Lim, Sean, Shah, Mcnair
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rational Synthesizers or Heuristic Followers? Analyzing LLMs in RAG-based Question-Answering
di: Naphade, Atharv
Pubblicazione: (2026)

Interpreting Affine Recurrence Learning in GPT-style Transformers
di: Bhargav, Samarth, et al.
Pubblicazione: (2024)

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

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts
di: Schoene, Annika M, et al.
Pubblicazione: (2025)

AssertBench: A Benchmark for Evaluating Self-Assertion in Large Language Models
di: Lee, Jaeho, et al.
Pubblicazione: (2025)

Introspective Diffusion Language Models
di: Yu, Yifan, et al.
Pubblicazione: (2026)

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

"I May Not Have Articulated Myself Clearly": Diagnosing Dynamic Instability in LLM Reasoning at Inference Time
di: Chen, Jinkun, et al.
Pubblicazione: (2026)

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

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

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

Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages
di: Cui, Brandon, et al.
Pubblicazione: (2026)

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

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
di: Ranganath, Suraj, et al.
Pubblicazione: (2026)

Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop
di: Goel, Atharv, et al.
Pubblicazione: (2025)

Emergent Introspective Awareness in Large Language Models
di: Lindsey, Jack
Pubblicazione: (2026)

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

InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspection
di: Jeon, Hayeon, et al.
Pubblicazione: (2026)

Agency in the Age of AI
di: Swarup, Samarth
Pubblicazione: (2025)

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

IntroLM: Introspective Language Models via Prefilling-Time Self-Evaluation
di: Kasnavieh, Hossein Hosseini, et al.
Pubblicazione: (2026)

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

SCRAMBLe : Enhancing Multimodal LLM Compositionality with Synthetic Preference Data
di: Mishra, Samarth, et al.
Pubblicazione: (2025)

Position: Introspective Experience from Conversational Environments as a Path to Better Learning
di: Musat, Claudiu Cristian, et al.
Pubblicazione: (2026)

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

Systems Explaining Systems: A Framework for Intelligence and Consciousness
di: Semmler, Sean Niklas
Pubblicazione: (2026)

Towards Optimizing the Costs of LLM Usage
di: Shekhar, Shivanshu, et al.
Pubblicazione: (2024)

LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
di: Veldanda, Akshaj Kumar, et al.
Pubblicazione: (2024)

Context Branching for LLM Conversations: A Version Control Approach to Exploratory Programming
di: Nanjundappa, Bhargav Chickmagalur, et al.
Pubblicazione: (2025)

Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging
di: Su, Guinan, et al.
Pubblicazione: (2025)

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

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

Does It Make Sense to Speak of Introspection in Large Language Models?
di: Comsa, Iulia M., et al.
Pubblicazione: (2025)

Chatting with Images for Introspective Visual Thinking
di: Wu, Junfei, et al.
Pubblicazione: (2026)

AI, Help Me Think$\unicode{x2014}$but for Myself: Assisting People in Complex Decision-Making by Providing Different Kinds of Cognitive Support
di: Reicherts, Leon, et al.
Pubblicazione: (2025)

Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent
di: He, Zeyu, et al.
Pubblicazione: (2025)

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

Zero-Overhead Introspection for Adaptive Test-Time Compute
di: Manvi, Rohin, et al.
Pubblicazione: (2025)

Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
di: Hosseini, Hadi, et al.
Pubblicazione: (2025)

The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
di: Shah, Raj Sanjay, et al.
Pubblicazione: (2026)