Cover Image

Detecting the Disturbance: A Nuanced View of Introspective Abilities in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hahami, Ely, Sinha, Ishaan, Jain, Lavik, Kaplan, Josh, Hahami, Jon
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Memorization and Knowledge Injection in Gated LLMs
by: Pan, Xu, et al.
Published: (2025)

Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs
by: Pan, Xu, et al.
Published: (2025)

User-Assistant Bias in LLMs
by: Pan, Xu, et al.
Published: (2025)

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

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

Toward Revealing Nuanced Biases in Medical LLMs
by: Adiba, Farzana Islam, et al.
Published: (2025)

Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior
by: Toy, Jason, et al.
Published: (2024)

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

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

Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization
by: Verma, Ishaan, et al.
Published: (2025)

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

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

NiceWebRL: a Python library for human subject experiments with reinforcement learning environments
by: Carvalho, Wilka, et al.
Published: (2025)

Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances
by: Wu, Zehui, et al.
Published: (2024)

Unified Smart Factory Model: A model-based Approach for Integrating Industry 4.0 and Sustainability for Manufacturing Systems
by: Kaushal, Ishaan, et al.
Published: (2025)

Zero-Training Temporal Drift Detection for Transformer Sentiment Models: A Comprehensive Analysis on Authentic Social Media Streams
by: Bansal, Aayam, et al.
Published: (2025)

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

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

MicroProbe: Efficient Reliability Assessment for Foundation Models with Minimal Data
by: Bansal, Aayam, et al.
Published: (2025)

AgentComm-Bench: Stress-Testing Cooperative Embodied AI Under Latency, Packet Loss, and Bandwidth Collapse
by: Bansal, Aayam, et al.
Published: (2026)

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

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

Enhancing Low-Resource Minority Language Translation with LLMs and Retrieval-Augmented Generation for Cultural Nuances
by: Chang, Chen-Chi, et al.
Published: (2025)

Safeguarding AI Agents: Developing and Analyzing Safety Architectures
by: Domkundwar, Ishaan, et al.
Published: (2024)

CAND: Cross-Domain Ambiguity Inference for Early Detecting Nuanced Illness Deterioration
by: Ting, Lo Pang-Yun, et al.
Published: (2025)

Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench
by: Narad, Reuben, et al.
Published: (2025)

Improving LLMs' Generalized Reasoning Abilities by Graph Problems
by: Zhang, Qifan, et al.
Published: (2025)

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

Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs
by: Cheng, Kewei, et al.
Published: (2024)

Trained Miniatures: Low cost, High Efficacy SLMs for Sales & Marketing
by: Bhola, Ishaan, et al.
Published: (2025)

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)

The Counterfeit Conundrum: Can Code Language Models Grasp the Nuances of Their Incorrect Generations?
by: Gu, Alex, et al.
Published: (2024)

Longitudinal Boundary Sharpness Coefficient Slopes Predict Time to Alzheimer's Disease Conversion in Mild Cognitive Impairment: A Survival Analysis Using the ADNI Cohort
by: Cherukuri, Ishaan
Published: (2026)

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

Diversity of Thought Improves Reasoning Abilities of LLMs
by: Naik, Ranjita, et al.
Published: (2023)

SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer
by: Gautam, Anmol, et al.
Published: (2024)

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

Light-Weight Benchmarks Reveal the Hidden Hardware Cost of Zero-Shot Tabular Foundation Models
by: Gangwani, Ishaan, et al.
Published: (2025)

Reason-to-Transmit: Deliberative Adaptive Communication for Cooperative Perception
by: Bansal, Aayam, et al.
Published: (2026)