Image de couverture de livre

Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Ruichen, Yan, Wenjing, Zhang, Ying-Jun Angela
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Provable Knowledge Acquisition and Extraction in One-Layer Transformers
par: Xu, Ruichen, et autres
Publié: (2025)

Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
par: Hellwig, Philipp, et autres
Publié: (2026)

Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data
par: Xing, Yue, et autres
Publié: (2024)

Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
par: Zhu, Hanlin, et autres
Publié: (2024)

Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective
par: Shao, Jintian, et autres
Publié: (2025)

LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance
par: Haller, Patrick, et autres
Publié: (2025)

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
par: Huang, Yixiao, et autres
Publié: (2025)

Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
par: Havrilla, Alex, et autres
Publié: (2024)

GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding
par: Yan, Yibo, et autres
Publié: (2024)

Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
par: Bombari, Simone, et autres
Publié: (2024)

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
par: Zhang, Zhongwang, et autres
Publié: (2025)

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
par: Cui, Yingqian, et autres
Publié: (2024)

Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
par: Opiełka, Gustaw, et autres
Publié: (2025)

Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
par: Vasudeva, Bhavya, et autres
Publié: (2026)

Tackling Privacy Heterogeneity in Differentially Private Federated Learning
par: Xu, Ruichen, et autres
Publié: (2026)

Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability
par: Xu, Chenhui, et autres
Publié: (2025)

A Theoretical Understanding of Self-Correction through In-context Alignment
par: Wang, Yifei, et autres
Publié: (2024)

Evaluating the Robustness of Analogical Reasoning in Large Language Models
par: Lewis, Martha, et autres
Publié: (2024)

Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
par: Gan, Zeyu, et autres
Publié: (2024)

Understanding Addition and Subtraction in Transformers
par: Quirke, Philip, et autres
Publié: (2024)

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
par: Li, Zihao, et autres
Publié: (2025)

Reasoning in Transformers -- Mitigating Spurious Correlations and Reasoning Shortcuts
par: Enström, Daniel, et autres
Publié: (2024)

Towards Understanding Steering Strength
par: Taimeskhanov, Magamed, et autres
Publié: (2026)

JSAM: Privacy Straggler-Resilient Joint Client Selection and Incentive Mechanism Design in Differentially Private Federated Learning
par: Xu, Ruichen, et autres
Publié: (2026)

X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
par: Liu, Qianchu, et autres
Publié: (2025)

Benchmarking and Understanding Compositional Relational Reasoning of LLMs
par: Ni, Ruikang, et autres
Publié: (2024)

Understanding Hidden Computations in Chain-of-Thought Reasoning
par: Bharadwaj, Aryasomayajula Ram
Publié: (2024)

Reasoning Beyond Literal: Cross-style Multimodal Reasoning for Figurative Language Understanding
par: Cheshmi, Seyyed Saeid, et autres
Publié: (2026)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
par: Wang, Xu, et autres
Publié: (2025)

Transformers meet Neural Algorithmic Reasoners
par: Bounsi, Wilfried, et autres
Publié: (2024)

Observable Propagation: Uncovering Feature Vectors in Transformers
par: Dunefsky, Jacob, et autres
Publié: (2023)

GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
par: Duan, Jinhao, et autres
Publié: (2024)

Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors
par: Rofin, Mark, et autres
Publié: (2026)

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition
par: He, Zhengfu, et autres
Publié: (2025)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
par: Li, Hongkang, et autres
Publié: (2024)

Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning
par: Liu, Chi, et autres
Publié: (2025)

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
par: McGovern, Hope, et autres
Publié: (2026)

Extracting Rule-based Descriptions of Attention Features in Transformers
par: Friedman, Dan, et autres
Publié: (2025)

A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
par: Zhang, Yuyang, et autres
Publié: (2026)

DisEmbed: Transforming Disease Understanding through Embeddings
par: Faroz, Salman
Publié: (2024)