LLMs Crystallize Factual Knowledge Late in Layers, Study Finds

Researchers have identified a phenomenon called "Late Crystallization" in large language models, where factual knowledge primarily emerges in the final layers rather than gradually across all layers. This finding, observed across multiple model families like Pythia, Gemma, and Llama-3.1, suggests that factual recall is concentrated towards the end of the model's processing. The study also proposes a new intervention principle based on this crystallization and introduces a spectrum distinguishing between computable and memorized knowledge. AI

IMPACT Reveals that LLMs store factual knowledge late, potentially guiding future model design and intervention strategies for accuracy.

RANK_REASON This is a research paper detailing a new finding about LLM knowledge crystallization. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• Gemma
• Llama-3.1
• MMLU
• MechLens
• Pythia
• Qwen2.5

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →