Sycophancy Hides Linearly in the Attention Heads

We find that correct-to-incorrect sycophancy signals are most linearly accessible within multi-head attention activations. Motivated by the linear representation hypothesis, we train linear probes across the residual stream, multilayer perceptron (MLP), and attention layers to analyze where these signals emerge. Although separability appears in the residual stream and MLPs, steering using these probes is most effective in a sparse subset of middle-layer attention heads. Using TruthfulQA as the base dataset, we find that probes trained on it transfer effectively to other factual QA benchmarks. Furthermore, comparing our discovered direction to previously identified “truthful” directions reveals limited overlap, suggesting that factual accuracy, and deference resistance, arise from related but distinct mechanisms. Attention-pattern analysis further indicates that the influential heads attend disproportionately to expressions of user doubt, contributing to sycophantic shifts. Overall, these findings suggest that sycophancy can be mitigated through simple, targeted linear interventions that exploit the internal geometry of attention activations. Code will be released upon publication.

Citation

R.A. Genadi, M.S. Nwadike, N. Mukhituly, T. Hiraoka, H. AlQuabeh, K. Inui, "Sycophancy Hides Linearly in the Attention Heads," 2026, pp. 6896-6912.

Conference

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Source

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Publisher

Association for Computational Linguistics

DOI

10.18653/v1/2026.eacl-long.324

Additional links

https://aclanthology.org/2026.eacl-long.324/