From Geometry to Behavior: How Instruction Exposure Unlocks Latent Rhetorical Directions in LLMs

The paper investigates whether language models possess latent rhetorical abilities, specifically analogy reasoning, before instruction tuning. By extracting an "Analogy Vector" from the residual stream, the authors demonstrate that this vector can steer explanation style across several instruction-tuned models, improving performance metrics. Their findings reveal a continuous gradient of behavioral accessibility tied to the amount of instruction exposure during training, challenging the binary base‑vs‑instruct distinction and suggesting that instruction exposure shapes rhetorical knowledge in activation space.

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.

• llms
• fine-tuning
• safety