Image de couverture de livre

Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Brumley, Madeline, Kwon, Joe, Krueger, David, Krasheninnikov, Dmitrii, Anwar, Usman
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Understanding (Un)Reliability of Steering Vectors in Language Models
par: Braun, Joschka, et autres
Publié: (2025)

Implicit meta-learning may lead language models to trust more reliable sources
par: Krasheninnikov, Dmitrii, et autres
Publié: (2023)

Fresh in memory: Training-order recency is linearly encoded in language model activations
par: Krasheninnikov, Dmitrii, et autres
Publié: (2025)

Stress-Testing Capability Elicitation With Password-Locked Models
par: Greenblatt, Ryan, et autres
Publié: (2024)

Hierarchical Synthetic Tabular Data Generation: A Hybrid Top-Down and Bottom-Up Framework
par: Nie, Junfeng, et autres
Publié: (2026)

Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens
par: Anwar, Usman, et autres
Publié: (2024)

Defining and Characterizing Reward Hacking
par: Skalse, Joar, et autres
Publié: (2022)

Reward Model Ensembles Help Mitigate Overoptimization
par: Coste, Thomas, et autres
Publié: (2023)

ReeFRAME: Reeb Graph based Trajectory Analysis Framework to Capture Top-Down and Bottom-Up Patterns of Life
par: Gudavalli, Chandrakanth, et autres
Publié: (2024)

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

Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games
par: Anwar, Usman, et autres
Publié: (2024)

Detecting High-Stakes Interactions with Activation Probes
par: McKenzie, Alex, et autres
Publié: (2025)

Learning to Forget using Hypernetworks
par: Rangel, Jose Miguel Lara, et autres
Publié: (2024)

Eliciting Latent Knowledge from Quirky Language Models
par: Mallen, Alex, et autres
Publié: (2023)

Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts
par: Qian, Kun, et autres
Publié: (2025)

Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
par: Srinivasan, Ravi, et autres
Publié: (2023)

Chapter Comparing Top-Down And Bottom-Up Approaches. Maps Of Cultural Landscape Digitisation Processes
par: Vedoà, Marco
Publié: (2022)

Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty
par: Ataei, Masoud, et autres
Publié: (2025)

Mitigating Goal Misgeneralization via Minimax Regret
par: Sadek, Karim Abdel, et autres
Publié: (2025)

Attention Down-Sampling Transformer, Relative Ranking and Self-Consistency for Blind Image Quality Assessment
par: Alsaafin, Mohammed, et autres
Publié: (2024)

Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
par: Park, Jongho, et autres
Publié: (2024)

Top-Down Bayesian Posterior Sampling for Sum-Product Networks
par: Yokoi, Soma, et autres
Publié: (2024)

BUILD with Precision: Bottom-Up Inference of Linear DAGs
par: Ajorlou, Hamed, et autres
Publié: (2025)

Productively Deploying Emerging Models on Emerging Platforms: A Top-Down Approach for Testing and Debugging
par: Feng, Siyuan, et autres
Publié: (2024)

Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision
par: Kalluri, Tarun, et autres
Publié: (2023)

Transformers as Implicit State Estimators: In-Context Learning in Dynamical Systems
par: Akram, Usman, et autres
Publié: (2024)

Contextual Feedback Loops: Amplifying Deep Reasoning with Iterative Top-Down Feedback
par: Fein-Ashley, Jacob, et autres
Publié: (2024)

Representation Engineering: A Top-Down Approach to AI Transparency
par: Zou, Andy, et autres
Publié: (2023)

Taking the Next Step: Bottom‐Up and Top‐Down Approaches for Mental Health Equity
par: Alexandria G. Bauer, et autres
Publié: (2026)

IM-Context: In-Context Learning for Imbalanced Regression Tasks
par: Nejjar, Ismail, et autres
Publié: (2024)

Context-Scaling versus Task-Scaling in In-Context Learning
par: Abedsoltan, Amirhesam, et autres
Publié: (2024)

The Impact of Off-Policy Training Data on Probe Generalisation
par: Kirch, Nathalie, et autres
Publié: (2025)

Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study
par: Li, Danya, et autres
Publié: (2026)

Think Outside the Policy: In-Context Steered Policy Optimization
par: Huang, Hsiu-Yuan, et autres
Publié: (2025)

Position: AI Scaling: From Up to Down and Out
par: Wang, Yunke, et autres
Publié: (2025)

Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning
par: Siddika, Fatema, et autres
Publié: (2026)

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
par: Sharma, Kartik, et autres
Publié: (2026)

Enhancing Time-Series Anomaly Detection by Integrating Spectral-Residual Bottom-Up Attention with Reservoir Computing
par: Nihei, Hayato, et autres
Publié: (2025)

Beyond Top-Down and Bottom-Up- Cognition as Context-Dependent Emergence in a Complex Adaptive Brain
par: Topcular, Baris, et autres
Publié: (2025)

Learning to Order: Task Sequencing as In-Context Optimization
par: Kobiolka, Jan, et autres
Publié: (2026)