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

Koki Itai, Jun Hirako, Hiroaki Yamagiwa

Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment: 5 upvotes on Hugging Face Daily Papers, #22 of 42 papers on 2026-11-17. Day-by-day upvote history.

Upvotes over time

It had 5 upvotes by the next day, 5 upvotes by day 3, 5 upvotes by day 7, and has 5 now. It ranked #75 of 146 papers in its week and #323 of 520 in its month.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.