Imagen de Portada

Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qin, Tian, Saphra, Naomi, Alvarez-Melis, David
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Can Interpretation Predict Behavior on Unseen Data?
por: Li, Victoria R., et al.
Publicado: (2025)

Mechanistic?
por: Saphra, Naomi, et al.
Publicado: (2024)

Fast Forwarding Low-Rank Training
por: Rahamim, Adir, et al.
Publicado: (2024)

TRAM: Bridging Trust Regions and Sharpness Aware Minimization
por: Sherborne, Tom, et al.
Publicado: (2023)

Continuous Language Model Interpolation for Dynamic and Controllable Text Generation
por: Kangaslahti, Sara, et al.
Publicado: (2024)

Random Scaling of Emergent Capabilities
por: Zhao, Rosie, et al.
Publicado: (2025)

Do Activation Verbalization Methods Convey Privileged Information?
por: Li, Millicent, et al.
Publicado: (2025)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
por: Kim, Jeonghye, et al.
Publicado: (2026)

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
por: van der Wal, Oskar, et al.
Publicado: (2025)

Attribute Diversity Determines the Systematicity Gap in VQA
por: Berlot-Attwell, Ian, et al.
Publicado: (2023)

Using Shapley interactions to understand how models use structure
por: Singhvi, Divyansh, et al.
Publicado: (2024)

Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
por: Shen, Junhong, et al.
Publicado: (2024)

Decomposing Elements of Problem Solving: What "Math" Does RL Teach?
por: Qin, Tian, et al.
Publicado: (2025)

CharED: Character-wise Ensemble Decoding for Large Language Models
por: Gu, Kevin, et al.
Publicado: (2024)

A Label is Worth a Thousand Images in Dataset Distillation
por: Qin, Tian, et al.
Publicado: (2024)

Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
por: Öncel, Fırat, et al.
Publicado: (2024)

Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure
por: Maheshwari, Gaurav, et al.
Publicado: (2024)

Adapting Language Models via Token Translation
por: Feng, Zhili, et al.
Publicado: (2024)

TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
por: Sun, Hanshi, et al.
Publicado: (2024)

Why Prompt Optimization Works, and Why It Sometimes Doesn't: A Causal-Inspired Edit-Level Analysis
por: Gong, Shuzhi, et al.
Publicado: (2026)

Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers
por: Ahuja, Kabir, et al.
Publicado: (2024)

ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining
por: Bal, Melis Ilayda, et al.
Publicado: (2025)

Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
por: Rohweder, Jonas, et al.
Publicado: (2026)

Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning
por: Lin, Chaofan, et al.
Publicado: (2025)

When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
por: Hadeliya, Tsimur, et al.
Publicado: (2025)

Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation
por: Sorokin, Nikita, et al.
Publicado: (2026)

Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs
por: Bansal, Rachit, et al.
Publicado: (2025)

Hidden Breakthroughs in Language Model Training
por: Kangaslahti, Sara, et al.
Publicado: (2025)

HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing
por: He, Zifan, et al.
Publicado: (2024)

Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling
por: Li, Anqi, et al.
Publicado: (2025)

EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees
por: Zeng, Zhiyuan, et al.
Publicado: (2025)

HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification
por: Jain, Vidit, et al.
Publicado: (2024)

Distributional Dataset Distillation with Subtask Decomposition
por: Qin, Tian, et al.
Publicado: (2024)

Data Augmentations for Improved (Large) Language Model Generalization
por: Feder, Amir, et al.
Publicado: (2023)

Dissecting Linear Recurrent Models: How Different Gating Strategies Drive Selectivity and Generalization
por: Bouhadjar, Younes, et al.
Publicado: (2026)

Unraveling the Mystery of Scaling Laws: Part I
por: Su, Hui, et al.
Publicado: (2024)

Instruction Diversity Drives Generalization To Unseen Tasks
por: Zhang, Dylan, et al.
Publicado: (2024)

Reducing Text Bias in Synthetically Generated MCQAs for VLMs in Autonomous Driving
por: Kulgod, Sutej, et al.
Publicado: (2026)

DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning
por: He, Yongxin, et al.
Publicado: (2025)

Generative Data Refinement: Just Ask for Better Data
por: Jiang, Minqi, et al.
Publicado: (2025)