cs.CLNov 16, 2026

Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment

Authors: Koki Itai, Jun Hirako, Hiroaki Yamagiwa

Organizations: SB Intuitions Corp.

Abstract

Abstention, the withholding of a response by a large language model (LLM) under uncertainty or safety risks, is essential for trustworthy models. The causes of abstention fall into three perspectives: ambiguity in the Query (Q), limits of Model Knowledge (MK), and misalignment with Human Values (HV). However, prior analyses of internal representations have focused on HV, using a refusal direction computed from harmful and harmless queries. No study has analyzed the three perspectives jointly. We therefore extend the refusal direction framework to all three perspectives. Specifically, for each perspective, we construct counterfactual pairs that share a template and differ only in the abstention-inducing factor, and compute an abstention direction by normalizing the difference in mean activations between the two polarities. Activation steering experiments show that intervening in middle layers increases or decreases abstention across all three perspectives. Moreover, steering yields cross-perspective effects, indicating that the abstention directions share a common directional component.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty

    Jul 22, 2025Zipeng Ling, Shuliang Liu, Yuehao Tang +8LLM AbstentionLLM Uncertainty Estimation

  2. Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs

    Apr 2, 2026Abinitha Gourabathina, Inkit Padhi, Manish Nagireddy +2LLM AbstentionLLM Hallucination Mitigation

  3. Strong yet Controllable LLM Abstention without Learning to Abstain

    Oct 12, 2026Junwei Zhang, Yifei Wang, Wanli Yang +6Factual QALLM Abstention