Image de couverture de livre

Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Czech, Eric, Xu, Zhiwei, Elmatad, Yael, Wang, Yixin, Held, William
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
par: Thangarasa, Vithursan, et autres
Publié: (2023)

Discrete Tokenization Unlocks Transformers for Calibrated Tabular Forecasting
par: Elmatad, Yael S.
Publié: (2026)

Reconciling Kaplan and Chinchilla Scaling Laws
par: Pearce, Tim, et autres
Publié: (2024)

FLOP-Efficient Training: Early Stopping Based on Test-Time Compute Awareness
par: Amer, Hossam, et autres
Publié: (2026)

Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
par: Sardana, Nikhil, et autres
Publié: (2023)

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs
par: Ling Team, et autres
Publié: (2025)

Machine Learning Approaches for Mental Illness Detection on Social Media: A Systematic Review of Biases and Methodological Challenges
par: Cao, Yuchen, et autres
Publié: (2024)

How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
par: Schwethelm, Kristian, et autres
Publié: (2026)

IsoQuant: Hardware-Aligned SO(4) Isoclinic Rotations for LLM KV Cache Compression
par: Ji, Zhongping
Publié: (2026)

XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning
par: Zhang, Zhihan, et autres
Publié: (2025)

Unintended Impacts of LLM Alignment on Global Representation
par: Ryan, Michael J., et autres
Publié: (2024)

Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning
par: Dijujin, Negin Hashemi, et autres
Publié: (2025)

Relative Value Biases in Large Language Models
par: Hayes, William M., et autres
Publié: (2024)

Large Language Models are Biased Reinforcement Learners
par: Hayes, William M., et autres
Publié: (2024)

From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When
par: Wibisono, Kevin Christian, et autres
Publié: (2024)

ABCD: All Biases Come Disguised
par: Nowak, Mateusz, et autres
Publié: (2026)

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
par: Opedal, Andreas, et autres
Publié: (2024)

Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times
par: Oh, Byung-Doh, et autres
Publié: (2024)

Can Large Language Models Transform Computational Social Science?
par: Ziems, Caleb, et autres
Publié: (2023)

EqualizeIR: Mitigating Linguistic Biases in Retrieval Models
par: Cheng, Jiali, et autres
Publié: (2025)

Language Models Need Inductive Biases to Count Inductively
par: Chang, Yingshan, et autres
Publié: (2024)

Silenced Biases: The Dark Side LLMs Learned to Refuse
par: Himelstein, Rom, et autres
Publié: (2025)

Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognition
par: Huber, Christian, et autres
Publié: (2025)

Controlled LLM Decoding via Discrete Auto-regressive Biasing
par: Pynadath, Patrick, et autres
Publié: (2025)

No One Size Fits All: QueryBandits for Hallucination Mitigation
par: Cho, Nicole, et autres
Publié: (2026)

FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
par: Wang, Qianli, et autres
Publié: (2025)

Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
par: Hu, Michael Y., et autres
Publié: (2025)

Understanding Intrinsic Socioeconomic Biases in Large Language Models
par: Arzaghi, Mina, et autres
Publié: (2024)

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

Self-Speculative Biased Decoding for Faster Re-Translation
par: Zeng, Linxiao, et autres
Publié: (2025)

One Size Fits None: Heuristic Collapse in LLM Investment Advice
par: Ross, Jillian, et autres
Publié: (2026)

Neural-Symbolic Recursive Machine for Systematic Generalization
par: Li, Qing, et autres
Publié: (2022)

Reinforcement Learning with Conditional Expectation Reward
par: Xiao, Changyi, et autres
Publié: (2026)

Understanding Reference Policies in Direct Preference Optimization
par: Liu, Yixin, et autres
Publié: (2024)

Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
par: Wang, Zhiwei, et autres
Publié: (2024)

Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws
par: Jha, Akshita, et autres
Publié: (2024)

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
par: Ye, Jiayuan, et autres
Publié: (2026)

BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
par: Ben-Zaken, Elad, et autres
Publié: (2021)

Toward Automated Detection of Biased Social Signals from the Content of Clinical Conversations
par: Chen, Feng, et autres
Publié: (2024)

A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
par: Pfohl, Stephen R., et autres
Publié: (2024)