Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs
cs.CL
Submitted: 2025-05-14
Updated: 2026-11-04
Code: https://github.com/frankniujc/entrainment
Terminology
Sources
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Language Models are Few-Shot Learners
- Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning
- Memorization in In-Context Learning
- The Hydra Effect: Emergent Self-repair in Language Model Computations
- LLaMA: Open and Efficient Foundation Language Models
- Measuring short-form factuality in large language models
- Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity
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