From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
Read the original on arXiv AI →The paper investigates how large language models (LLMs) such as Qwen, Llama, and Gemma use internal knowledge when answering questions. By performing layer‑wise interventions on the hidden state after the question, the authors compare how different request directions (pair‑conditioned vs. global) and answer types (noun, adjective, code) influence the model’s routing of information. The study finds that the influence of request direction varies across models and layers, with some models showing a sustained routing effect while others do not, highlighting distinct patterns of early readability, causal steering, and later content dependence.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.