Abstention in large language models arises from query ambiguity, model knowledge limits, and value misalignment, and steering internal activations in middle layers can increase or decrease abstention across these causes.
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…
abstentionlarge language model (LLM)uncertaintysafety risksrefusal directioninternal representationsharmful and harmless queriescounterfactual pairsabstention-inducing factorabstention direction
- Upvotes
- 6
- Authors
- 3
- Published
- Nov 16, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.