Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures
cs.CL
Submitted: 2026-06-15
Updated: 2026-11-09
Terminology
Sources
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Universal Refusal Circuits Across LLMs: Cross-Model Transfer via Trajectory Replay and Concept-Basis Reconstruction
- Gemma 2: Improving Open Language Models at a Practical Size
- The Llama 3 Herd of Models
- Controllable and explainable personality sliders for LLMs at inference time
- Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts
- The Platonic Representation Hypothesis
- Mistral 7B
- Probing then Editing Response Personality of Large Language Models
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
- Activation Space Interventions Can Be Transferred Between Large Language Models
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- Transferring Linear Features Across Language Models With Model Stitching
- Linear Representations of Sentiment in Large Language Models
- On the Non-Identifiability of Steering Vectors in Large Language Models
- Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures
- Qwen2.5 Technical Report
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