Scale, Drivers, and Limits of Representational Alignment Across Large Language Models
cs.CL, cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/twitter/twemoji
Terminology
Sources
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- The Llama 3 Herd of Models
- The Platonic Representation Hypothesis
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Mistral 7B
- Soft Matching Distance: A metric on neural representations that captures single-neuron tuning
- Shared Global and Local Geometry of Language Model Embeddings
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Qwen2.5 Technical Report
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering