Imagen de Portada

Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Kaiyu, Mian, Zhang, Wu, Peilin, Du, Xinya, Chen, Zhiyu
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GEAR: A General Evaluation Framework for Abductive Reasoning
por: He, Kaiyu, et al.
Publicado: (2025)

HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
por: Wu, Peilin, et al.
Publicado: (2025)

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty
por: Wu, Peilin, et al.
Publicado: (2025)

IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction
por: He, Kaiyu, et al.
Publicado: (2024)

From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models
por: He, Kaiyu, et al.
Publicado: (2025)

Do Retrieval-Augmented Language Models Adapt to Varying User Needs?
por: Wu, Peilin, et al.
Publicado: (2025)

AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning
por: Wu, Peilin, et al.
Publicado: (2026)

PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations
por: Li, Ruosen, et al.
Publicado: (2023)

LDC: Learning to Generate Research Idea with Dynamic Control
por: Li, Ruochen, et al.
Publicado: (2024)

Long Story Generation via Knowledge Graph and Literary Theory
por: Shi, Ge, et al.
Publicado: (2025)

Logical Reasoning over Natural Language as Knowledge Representation: A Survey
por: Yang, Zonglin, et al.
Publicado: (2023)

Extrapolation by Association: Length Generalization Transfer in Transformers
por: Cai, Ziyang, et al.
Publicado: (2025)

MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents
por: Li, Ruochen, et al.
Publicado: (2024)

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery
por: Yang, Zonglin, et al.
Publicado: (2023)

FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
por: Zhang, Runzhe, et al.
Publicado: (2026)

FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model
por: Wu, Xiaobao, et al.
Publicado: (2024)

Critical Data Size of Language Models from a Grokking Perspective
por: Zhu, Xuekai, et al.
Publicado: (2024)

RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks
por: Wu, Mian, et al.
Publicado: (2025)

Kwai-STaR: Transform LLMs into State-Transition Reasoners
por: Lu, Xingyu, et al.
Publicado: (2024)

LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
por: Yan, Shuo, et al.
Publicado: (2025)

How do Transformer Embeddings Represent Compositions? A Functional Analysis
por: Nagar, Aishik, et al.
Publicado: (2025)

Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT
por: Tao, Zhen, et al.
Publicado: (2024)

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
por: Jing, Liqiang, et al.
Publicado: (2024)

CircuitSynth: Reliable Synthetic Data Generation
por: Cheng, Zehua, et al.
Publicado: (2026)

CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
por: Zhang, Mian, et al.
Publicado: (2024)

Language Models as Inductive Reasoners
por: Yang, Zonglin, et al.
Publicado: (2022)

Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
por: Wu, Zijun, et al.
Publicado: (2023)

Transformer Circuit Faithfulness Metrics are not Robust
por: Miller, Joseph, et al.
Publicado: (2024)

Measuring Diversity in Synthetic Datasets
por: Zhu, Yuchang, et al.
Publicado: (2025)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
por: Wang, Xu, et al.
Publicado: (2025)

CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning
por: He, Zheqi, et al.
Publicado: (2024)

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
por: Huan, Maggie, et al.
Publicado: (2025)

FCKT: Fine-Grained Cross-Task Knowledge Transfer with Semantic Contrastive Learning for Targeted Sentiment Analysis
por: Chen, Wei, et al.
Publicado: (2025)

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
por: Cheng, Pengzhou, et al.
Publicado: (2024)

Circuit Complexity Bounds for RoPE-based Transformer Architecture
por: Chen, Bo, et al.
Publicado: (2024)

Do LLMs "Feel"? Emotion Circuits Discovery and Control
por: Wang, Chenxi, et al.
Publicado: (2025)

A Comprehensive Framework for Semantic Similarity Analysis of Human and AI-Generated Text Using Transformer Architectures and Ensemble Techniques
por: Gao, Lifu, et al.
Publicado: (2025)

Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers
por: Senel, Lütfi Kerem, et al.
Publicado: (2024)

Beyond Transfer Accuracy: Faithful Circuits for Controlled Low-Resource Adaptation
por: Nur'aini, Khumaisa, et al.
Publicado: (2026)

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
por: Chen, Han, et al.
Publicado: (2025)