Cover Image

Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lourie, Nicholas, Hu, Michael Y., Cho, Kyunghyun
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Neural Neural Scaling Laws
by: Hu, Michael Y., et al.
Published: (2026)

Hyperparameter Loss Surfaces Are Simple Near their Optima
by: Lourie, Nicholas, et al.
Published: (2025)

Show Your Work with Confidence: Confidence Bands for Tuning Curves
by: Lourie, Nicholas, et al.
Published: (2023)

Temporal Generalization: A Reality Check
by: Madaan, Divyam, et al.
Published: (2025)

Aioli: A Unified Optimization Framework for Language Model Data Mixing
by: Chen, Mayee F., et al.
Published: (2024)

Scaling Laws for Downstream Task Performance of Large Language Models
by: Isik, Berivan, et al.
Published: (2024)

Hyperparameters in Continual Learning: A Reality Check
by: Cha, Sungmin, et al.
Published: (2024)

Scaling Laws for Predicting Downstream Performance in LLMs
by: Chen, Yangyi, et al.
Published: (2024)

Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks
by: Lee, Wilson Y.
Published: (2026)

Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time
by: Hu, Michael Y., et al.
Published: (2026)

On the Relationship Between the Choice of Representation and In-Context Learning
by: Marinescu, Ioana, et al.
Published: (2025)

Efficient semantic uncertainty quantification in language models via diversity-steered sampling
by: Park, Ji Won, et al.
Published: (2025)

Adapting Decoder-Based Language Models for Diverse Encoder Downstream Tasks
by: Suganthan, Paul, et al.
Published: (2025)

Predicting Task Performance with Context-aware Scaling Laws
by: Montgomery, Kyle, et al.
Published: (2025)

Exploring the Impact of a Transformer's Latent Space Geometry on Downstream Task Performance
by: Marbut, Anna C., et al.
Published: (2024)

Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling
by: Madaan, Divyam, et al.
Published: (2026)

Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
by: Cho, Sungjun, et al.
Published: (2025)

Language Models as Causal Effect Generators
by: Bynum, Lucius E. J., et al.
Published: (2024)

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective
by: Xu, Chengyin, et al.
Published: (2025)

Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text
by: Jarca, Andrei, et al.
Published: (2025)

Training Language Models with Language Feedback at Scale
by: Scheurer, Jérémy, et al.
Published: (2023)

Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning
by: Yang, Bangji, et al.
Published: (2026)

Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
by: Riabi, Arij, et al.
Published: (2021)

Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional
by: Madaan, Divyam, et al.
Published: (2025)

Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
by: Madaan, Divyam, et al.
Published: (2024)

Scaling Laws for Precision
by: Kumar, Tanishq, et al.
Published: (2024)

Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
by: Li, Miaomiao, et al.
Published: (2025)

VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models
by: Zhang, Hanling, et al.
Published: (2025)

Revisiting the Scaling Properties of Downstream Metrics in Large Language Model Training
by: Krajewski, Jakub, et al.
Published: (2025)

Forecasting Downstream Performance of LLMs With Proxy Metrics
by: Patel, Arkil, et al.
Published: (2026)

Scaling Laws For Mixed Quantization
by: Cao, Zeyu, et al.
Published: (2024)

To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining
by: Singh, Karan, et al.
Published: (2026)

Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
by: Zhou, Qinhao, et al.
Published: (2025)

FedEval-LLM: Federated Evaluation of Large Language Models on Downstream Tasks with Collective Wisdom
by: He, Yuanqin, et al.
Published: (2024)

Unified Scaling Laws for Compressed Representations
by: Panferov, Andrei, et al.
Published: (2025)

Parallel Scaling Law for Language Models
by: Chen, Mouxiang, et al.
Published: (2025)

Scaling Law for Quantization-Aware Training
by: Chen, Mengzhao, et al.
Published: (2025)

Reconciling Kaplan and Chinchilla Scaling Laws
by: Pearce, Tim, et al.
Published: (2024)

Scaling Laws for Multilingual Language Models
by: He, Yifei, et al.
Published: (2024)

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
by: Schaeffer, Rylan, et al.
Published: (2024)