Many Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism
Language models often abandon a correct answer when the prompt contains a cue, a hint toward a wrong option such as "I think the answer is B." Sycophancy and related biases show this failure. They are often studied separately and blamed on alignment. We test this view causally, tracing the attention heads behind these biases through the stages of two post-training pipelines. In multiple-choice tests on most models, four cue types rely largely on the same few heads, a shared circuit already present in pretrained models. Most base models follow cues in plain text. Fine-tuning a base model on about 200 generic assistant examples without cues activates these heads in chat format, so cue-follo...
| Authors | Prakhar Gupta, Terry Jingchen Zhang, Zhijing Jin |
|---|---|
| Primary category | cs.CL |
| Published | 16 October 2026 |
| Last updated at source | 16 October 2026 |
Popularity, last 5 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 23 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.