Metraipolis › archive › dc_73d1db72e300

When Steering Shifts Discourse: Identifying and Intervening on Discourse-Level Changes due to Activation Steering in LLMs — arXiv:2610.41661

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41661
License (as archived)
CC0-1.0
Archived
2026-11-02T07:10:44.376Z
SHA-256 of the archived text
718722ac2eae6cfea8cbe054e8d15104e3d424792edb7fe530c73ff5a833c4b5
Stable URL of this page
https://metraipolis.com/documento/dc_73d1db72e300

How to cite

When Steering Shifts Discourse: Identifying and Intervening on Discourse-Level Changes due to Activation Steering in LLMs — arXiv:2610.41661 — arXiv (en), https://arxiv.org/abs/2610.41661 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73d1db72e300 (Metraipolis archive dc_73d1db72e300, sha256 718722ac2eae6cfea8cbe054e8d15104e3d424792edb7fe530c73ff5a833c4b5)
BibTeX
@misc{dc73d1db72e300,
  title = {When Steering Shifts Discourse: Identifying and Intervening on Discourse-Level Changes due to Activation Steering in LLMs — arXiv:2610.41661},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41661},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73d1db72e300; sha256 718722ac2eae6cfea8cbe054e8d15104e3d424792edb7fe530c73ff5a833c4b5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41661. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Activation steering is an inference-time technique used to control or modify the behavior, tone, or safety properties of a large language model (LLM) without retraining the model's weights or editing its input prompt, but simply by adding a vector to its residual-stream activations. However, activation steering also changes the generated text in unintended ways, unrelated to intended behavior change, that are not well understood. Prior work has measured these changes only through coarse signals such as perplexity. In this work, we show that steering systematically produces significant changes in discourse dimensions of the generated text, such as its formality, use of evidence, and ambiguity. We present a way of countering this by adding a second, complementary vector that targets the affected discourse dimension. This intervention restores about 78% of the unintended discourse changes while preserving the intended steering behavior in about 93% of the generations.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41661 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T07:06:59.449Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).