Imagen de Portada

Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Martorell, Nicolas, Bianchi, Bruno
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Introspective Diffusion Language Models
por: Yu, Yifan, et al.
Publicado: (2026)

From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task
por: Martorell, Nicolas
Publicado: (2025)

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

Emergent Introspective Awareness in Large Language Models
por: Lindsey, Jack
Publicado: (2026)

Do Language Models Track Entities Across State Changes?
por: Tang, Zilu, et al.
Publicado: (2026)

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

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

Emotive Architectures: The Role of LLMs in Adjusting Work Environments
por: Vartziotis, Lara, et al.
Publicado: (2026)

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

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

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

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
por: Huo, Fushuo, et al.
Publicado: (2024)

Recursive Introspection: Teaching Language Model Agents How to Self-Improve
por: Qu, Yuxiao, et al.
Publicado: (2024)

Political Plasticity: An Analysis of Ideological Adaptability in Large Language Models
por: Bianchi, Bruno, et al.
Publicado: (2026)

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

Modeling cognitive processes of natural reading with transformer-based Language Models
por: Bianchi, Bruno, et al.
Publicado: (2025)

Teaching AI to Feel: A Collaborative, Full-Body Exploration of Emotive Communication
por: Tütüncü, Esen K., et al.
Publicado: (2025)

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

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

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

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

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

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

RIV: Recursive Introspection Mask Diffusion Vision Language Model
por: Li, YuQian, et al.
Publicado: (2025)

Tracking World States with Language Models: State-Based Evaluation Using Chess
por: Harang, Romain, et al.
Publicado: (2025)

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

Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Tracking
por: Kemper, Sara, et al.
Publicado: (2024)

Strategic Prompting for Conversational Tasks: A Comparative Analysis of Large Language Models Across Diverse Conversational Tasks
por: Joshi, Ratnesh Kumar, et al.
Publicado: (2024)

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

Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
por: Terzić, Aleksandar, et al.
Publicado: (2025)

Towards an Introspective Dynamic Model of Globally Distributed Computing Infrastructures
por: Kilic, Ozgur O., et al.
Publicado: (2025)

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

(How) Do Language Models Track State?
por: Li, Belinda Z., et al.
Publicado: (2025)

Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback
por: Alam, Md Zarif Ul, et al.
Publicado: (2026)

EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion
por: Wang, Haotian, et al.
Publicado: (2024)

Atlas-Alignment: Making Interpretability Transferable Across Language Models
por: Puri, Bruno, et al.
Publicado: (2025)

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

Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages
por: Almheiri, Saeed, et al.
Publicado: (2026)

Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading
por: Kim, Minkyung, et al.
Publicado: (2025)

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