Imagen de Portada

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pan, Zhikai, Liao, Chih-Ting, Liu, Chunrui, Xiao, Xi, Qiao, Yitong, Meng, Chunlei, Chen, Zhangquan, Cao, Xin
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

Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration
por: Liao, Chih-Ting, et al.
Publicado: (2025)

Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction
por: Shu, Bao, et al.
Publicado: (2025)

Do LLMs Build Spatial World Models? Evidence from Grid-World Maze Tasks
por: Li, Weijiang, et al.
Publicado: (2026)

Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
por: Zhang, Dapeng, et al.
Publicado: (2025)

Effective Learning for Small Reasoning Models: An Empirical Study on 0.5B Reasoning LLMs
por: Zhuang, Xialie, et al.
Publicado: (2025)

From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning
por: Tahmasbi, Amir, et al.
Publicado: (2025)

SIFThinker: Spatially-Aware Image Focus for Visual Reasoning
por: Chen, Zhangquan, et al.
Publicado: (2025)

Do Multilingual LLMs Think In English?
por: Schut, Lisa, et al.
Publicado: (2025)

PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs
por: Zhang, Pei, et al.
Publicado: (2025)

VisRL: Intention-Driven Visual Perception via Reinforced Reasoning
por: Chen, Zhangquan, et al.
Publicado: (2025)

Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner
por: Zhou, Yitong, et al.
Publicado: (2024)

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
por: Chen, Zhangquan, et al.
Publicado: (2025)

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

Do Multilingual LLMs have specialized language heads?
por: Naufil, Muhammad
Publicado: (2026)

Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning
por: Cao, Min, et al.
Publicado: (2025)

Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
por: Alam, Firoj, et al.
Publicado: (2026)

Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs
por: Chen, Kang, et al.
Publicado: (2025)

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
por: Kang, Deokhyung, et al.
Publicado: (2025)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
por: Zhao, Weixiang, et al.
Publicado: (2025)

Fast Diffusion Model For Seismic Data Noise Attenuation
por: Peng, Junheng, et al.
Publicado: (2024)

XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning
por: Zhang, Zhihan, et al.
Publicado: (2025)

Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs
por: Guo, Yanzhu, et al.
Publicado: (2024)

Searching for leptophilic composite asymmetric dark sector at $e^+e^-$ colliders
por: Lu, Chih-Ting, et al.
Publicado: (2025)

Assessing UWB‐RSOM for non‐invasive melanoma depth: Diagnostic potential and critical limitations
por: Shiuan‐Chih Chen, et al.
Publicado: (2025)

SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery
por: Cao, Meng, et al.
Publicado: (2025)

Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Test
por: Khandelwal, Aditi, et al.
Publicado: (2024)

From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs
por: Wu, Mingrui, et al.
Publicado: (2025)

Embodied AI: From LLMs to World Models
por: Feng, Tongtong, et al.
Publicado: (2025)

From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests
por: Tang, Luoxi, et al.
Publicado: (2025)

Scale-free Characteristics of Multilingual Legal Texts and the Limitations of LLMs
por: Chen, Haoyang, et al.
Publicado: (2025)

Topology-Agnostic Animal Motion Generation from Text Prompt
por: Chen, Keyi, et al.
Publicado: (2025)

Exploring Robustness of Multilingual LLMs on Real-World Noisy Data
por: Aliakbarzadeh, Amirhossein, et al.
Publicado: (2025)

SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models
por: Jiang, Peiyao, et al.
Publicado: (2026)

Reasoning or a Semblance of it? A Diagnostic Study of Transitive Reasoning in LLMs
por: Mehrafarin, Houman, et al.
Publicado: (2024)

Lowest Span Confidence: A Zero-Shot Metric for Efficient and Black-Box Hallucination Detection in LLMs
por: Qiao, Yitong, et al.
Publicado: (2026)

From HSIL to SCC : A Real‐World Analysis of Diagnostic Upgrade Pathways and Pitfalls in Cervical Cytology
por: Yan Qin, et al.
Publicado: (2026)

Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation
por: Cheng, Ziling, et al.
Publicado: (2025)

EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery
por: Xu, Zelin, et al.
Publicado: (2026)

Do Code LLMs Understand Design Patterns?
por: Pan, Zhenyu, et al.
Publicado: (2025)

Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?
por: Tam, Zhi Rui, et al.
Publicado: (2025)