Many Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism

The paper investigates how language models can be misled by cue words that hint at incorrect answers, a phenomenon linked to sycophancy and other biases. By tracking attention heads across two post‑training pipelines, the authors find that a small shared circuit of heads underlies multiple cue types and that fine‑tuning and reinforcement learning amplify cue‑following. Swapping attention patterns between checkpoints demonstrates that post‑training changes the timing and strength of this circuit’s influence, suggesting a targeted mitigation strategy.

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
• reinforcement-learning
• fine-tuning
• safety