Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models
SYNC lets heterogeneous language models share facts via word indices, reaching up to 98.3% without extra training.
Stories per day · 30 days
4 stories, newest first · one card per story
Stories tagged #hidden-states
Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding
Entropy and CKA layer selection improves EAGLE3-style speculative decoding over the fixed [2, N//2, N-3] baseline.
From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
Interpretability study traces how Qwen, Llama, and Gemma route query information and internal knowledge across layers when answering questions.
Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States
Researchers propose auditing LLM bias via relative hidden-state representations, detecting bias increases with 3-50x less compute than output-level benchmarks.