Metraipolis › archive › dc_574d55386dd2

Gated Activation Steering for Reducing Sycophancy & Hallucination in Medical Question Answering — arXiv:2608.23666

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23666
License (as archived)
CC0-1.0
Archived
2026-10-18T06:20:30.441Z
SHA-256 of the archived text
8a389d6c6e160ab21f023cc7973de3d45c258eccc16f986ae6ac690d1a831ddc
Stable URL of this page
https://metraipolis.com/documento/dc_574d55386dd2

How to cite

Gated Activation Steering for Reducing Sycophancy & Hallucination in Medical Question Answering — arXiv:2608.23666 — arXiv (en), https://arxiv.org/abs/2608.23666 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_574d55386dd2 (Metraipolis archive dc_574d55386dd2, sha256 8a389d6c6e160ab21f023cc7973de3d45c258eccc16f986ae6ac690d1a831ddc)
BibTeX
@misc{dc574d55386dd2,
  title = {Gated Activation Steering for Reducing Sycophancy & Hallucination in Medical Question Answering — arXiv:2608.23666},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23666},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_574d55386dd2; sha256 8a389d6c6e160ab21f023cc7973de3d45c258eccc16f986ae6ac690d1a831ddc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23666. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sycophancy and hallucination are persistent failure modes of Large Language Models (LLMs) across domains. However, it becomes particularly consequential in clinical question answering, where responses must remain grounded in the provided context and robust to user pressure. Hallucination can introduce information that is unsupported by the context, while sycophancy can cause a model to abandon a previously correct answer when challenged by the user. Existing approaches, such as prompt-based safeguards and always-on activation steering, often address these behaviors separately or apply interventions broadly across turns, which can unnecessarily deteriorate responses that were already correct. To address these limitations within a single framework, we employ Inference Time Intervention (ITI) to jointly control both behaviors by learning separate steering directions for hallucination and sycophancy from contrastive clinical pairs and applying them to causally verified attention heads. During runtime, behavior-specific gates then determine when intervention is needed: the hallucination component mitigates unsupported claims, while the sycophancy component mitigates answer shifts caused by user pressure. We evaluate this framework on clinical questions grounded in EHR data while keeping the model weights frozen. Across all evaluation settings, we conducted 15,900 model-response runs. Across 600 pressure trajectories for the 4-billion-parameter model, the unsteered model caved in 570 cases. At the same time, gated steering helped it last longer in 551 of them. It held its ground under pressure at levels comparable to those of models with more than 100 billion parameters, showing that targeted inference-time steering can improve robustness without intervening at every turn.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.23666 — 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 2026-10-18T06:17:29.390Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).