Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
cs.CL, cs.AI
Submitted: 2026-05-20
Updated: 2026-11-17
Code: https://github.com/ericwtodd/function_vectors
Terminology
Sources
- Deep Learning using Rectified Linear Units (ReLU)
- What learning algorithm is in-context learning? Investigations with linear models
- Hate Speech Dataset from a White Supremacy Forum
- Understanding Task Vectors in In-Context Learning: Emergence, Functionality, and Limitations
- Disentangling Latent Shifts of In-Context Learning with Weak Supervision
- Adaptive Task Vectors for Large Language Models
- When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
- Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention
- Decoupled Weight Decay Regularization
- In-context Learning and Induction Heads
- A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts
- Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
- In-Context Learning through the Bayesian Prism
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Emergent Abilities of Large Language Models
- An Explanation of In-context Learning as Implicit Bayesian Inference
- Qwen3 Technical Report
- Which Attention Heads Matter for In-Context Learning?
- What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data