Copertina

To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lazić, Nevena, Fowl, Liam, György, András, Szepesvári, Csaba
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

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
di: György, András, et al.
Pubblicazione: (2025)

Frontier LLMs Still Struggle with Simple Reasoning Tasks
di: Malek, Alan, et al.
Pubblicazione: (2025)

To Believe or Not to Believe Your LLM
di: Yadkori, Yasin Abbasi, et al.
Pubblicazione: (2024)

Balancing optimism and pessimism in offline-to-online learning
di: Sentenac, Flore, et al.
Pubblicazione: (2025)

Seeing the Unseen: Learning Basis Confounder Representations for Robust Traffic Prediction
di: Ji, Jiahao, et al.
Pubblicazione: (2023)

Seeing the Unseen: Zooming in the Dark with Event Cameras
di: Kai, Dachun, et al.
Pubblicazione: (2026)

Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation
di: Zhang, Jincheng, et al.
Pubblicazione: (2025)

Mitigating LLM Hallucinations via Conformal Abstention
di: Yadkori, Yasin Abbasi, et al.
Pubblicazione: (2024)

Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Models
di: Zhang, Jincheng, et al.
Pubblicazione: (2023)

Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
di: Yang, Xiao-Wen, et al.
Pubblicazione: (2025)

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

Neuro-Symbolic Data Generation for Math Reasoning
di: Li, Zenan, et al.
Pubblicazione: (2024)

Generating Unseen Code Tests In Infinitum
di: Zalmanovici, Marcel, et al.
Pubblicazione: (2024)

Integrating Symbolic Reasoning into Neural Generative Models for Design Generation
di: Jacobson, Maxwell Joseph, et al.
Pubblicazione: (2023)

Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models
di: Petruzzellis, Flavio, et al.
Pubblicazione: (2024)

Reasoning about the Unseen for Efficient Outdoor Object Navigation
di: Xie, Quanting, et al.
Pubblicazione: (2023)

Do Transformers Have the Ability for Periodicity Generalization?
di: Liu, Huanyu, et al.
Pubblicazione: (2026)

See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay
di: Baghel, Ashish, et al.
Pubblicazione: (2026)

Partition Tree Weighting for Non-Stationary Stochastic Bandits
di: Veness, Joel, et al.
Pubblicazione: (2025)

See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection
di: Wu, Zhiheng, et al.
Pubblicazione: (2026)

Evaluating the Logical Reasoning Abilities of Large Reasoning Models
di: Liu, Hanmeng, et al.
Pubblicazione: (2025)

What's in the Box? Reasoning about Unseen Objects from Multimodal Cues
di: Ying, Lance, et al.
Pubblicazione: (2025)

Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning
di: Miao, Ziqi, et al.
Pubblicazione: (2026)

Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomena
di: Prasad, Renjith, et al.
Pubblicazione: (2026)

Compositional Neuro-Symbolic Reasoning
di: Das, Anugyan, et al.
Pubblicazione: (2026)

Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions
di: Hong, Zijin, et al.
Pubblicazione: (2025)

Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers
di: Qin, Tian, et al.
Pubblicazione: (2025)

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

Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling
di: Fan, Jianan, et al.
Pubblicazione: (2024)

Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning
di: Yu, Haorui, et al.
Pubblicazione: (2025)

Abductive Symbolic Solver on Abstraction and Reasoning Corpus
di: Lim, Mintaek, et al.
Pubblicazione: (2024)

RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
di: Fernandez, Nigel, et al.
Pubblicazione: (2025)

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
di: Li, Tianle, et al.
Pubblicazione: (2025)

GeoSketch: A Neural-Symbolic Approach to Geometric Multimodal Reasoning with Auxiliary Line Construction and Affine Transformation
di: Weng, Shichao, et al.
Pubblicazione: (2025)

ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning
di: Yu, Xiaodong, et al.
Pubblicazione: (2024)

Rethinking the Foundations for Continual Reinforcement Learning
di: Elelimy, Esraa, et al.
Pubblicazione: (2025)

Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration
di: Pan, Yicheng, et al.
Pubblicazione: (2025)

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

LogicGraph : Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification
di: Wu, Yanrui, et al.
Pubblicazione: (2026)