Image de couverture de livre

Emergent properties with repeated examples

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Charton, François, Kempe, Julia
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
par: Feng, Yunzhen, et autres
Publié: (2024)

A Tale of Tails: Model Collapse as a Change of Scaling Laws
par: Dohmatob, Elvis, et autres
Publié: (2024)

Learning the greatest common divisor: explaining transformer predictions
par: Charton, François
Publié: (2023)

Iteration Head: A Mechanistic Study of Chain-of-Thought
par: Cabannes, Vivien, et autres
Publié: (2024)

Int2Int: a framework for mathematics with transformers
par: Charton, François
Publié: (2025)

Instruction Diversity Drives Generalization To Unseen Tasks
par: Zhang, Dylan, et autres
Publié: (2024)

Model Collapse Demystified: The Case of Regression
par: Dohmatob, Elvis, et autres
Publié: (2024)

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization
par: Zhang, Dylan, et autres
Publié: (2024)

Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
par: Su, Jingtong, et autres
Publié: (2024)

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
par: Su, Jingtong, et autres
Publié: (2025)

From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers
par: Zhang, Dylan, et autres
Publié: (2024)

Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
par: Bhardwaj, Dhrupad, et autres
Publié: (2025)

Soft Tokens, Hard Truths
par: Butt, Natasha, et autres
Publié: (2025)

Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
par: Rudner, Tim G. J., et autres
Publié: (2024)

A K-Means, Ward and DBSCAN repeatability study
par: Bertrand, Anthony, et autres
Publié: (2025)

Dual feature-based and example-based explanation methods
par: Konstantinov, Andrei V., et autres
Publié: (2024)

Model Organisms for Emergent Misalignment
par: Turner, Edward, et autres
Publié: (2025)

Convergent Linear Representations of Emergent Misalignment
par: Soligo, Anna, et autres
Publié: (2025)

Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks
par: Feng, Yunzhen, et autres
Publié: (2024)

Unlocking Emergent Modularity in Large Language Models
par: Qiu, Zihan, et autres
Publié: (2023)

Data curation via joint example selection further accelerates multimodal learning
par: Evans, Talfan, et autres
Publié: (2024)

Understanding Emergent Misalignment via Feature Superposition Geometry
par: Minegishi, Gouki, et autres
Publié: (2026)

Interpreting Emergent Planning in Model-Free Reinforcement Learning
par: Bush, Thomas, et autres
Publié: (2025)

Emergent Bias and Fairness in Multi-Agent Decision Systems
par: Madigan, Maeve, et autres
Publié: (2025)

In-Training Defenses against Emergent Misalignment in Language Models
par: Kaczér, David, et autres
Publié: (2025)

Simulating realistic short tandem repeat capillary electrophoretic signal using a generative adversarial network
par: Taylor, Duncan, et autres
Publié: (2024)

Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
par: Xu, Alec S., et autres
Publié: (2026)

Emergent Symbol-like Number Variables in Artificial Neural Networks
par: Grant, Satchel, et autres
Publié: (2025)

Emergent Risk Awareness in Rational Agents under Resource Constraints
par: Ornia, Daniel Jarne, et autres
Publié: (2025)

tinyBenchmarks: evaluating LLMs with fewer examples
par: Polo, Felipe Maia, et autres
Publié: (2024)

Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
par: Arturi, Daniel Aarao Reis, et autres
Publié: (2025)

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment
par: Arnold, Julian, et autres
Publié: (2025)

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
par: Haim, Shahar, et autres
Publié: (2026)

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
par: Kobayashi, Seijin, et autres
Publié: (2025)

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
par: Mushtaq, Erum, et autres
Publié: (2025)

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training
par: Labiad, Ismail, et autres
Publié: (2025)

Evidence of an Emergent "Self" in Continual Robot Learning
par: Jhunjhunwala, Adidev, et autres
Publié: (2026)

Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
par: Wen, Yuxiao, et autres
Publié: (2024)

Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration
par: Joo, Taejong, et autres
Publié: (2025)

NODE-AdvGAN: Improving the transferability and perceptual similarity of adversarial examples by dynamic-system-driven adversarial generative model
par: Xie, Xinheng, et autres
Publié: (2024)