Kejia Huang | Searcharxiv

arXiv2026

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

Large Language Models (LLMs) are increasingly trained to abstain from answering questions they are unsure about. However, this ability is often misused: in real-world applications, user prompts sometimes contain uncertainty elements, and driven by this, LLMs are inclined to abstain even on problems they are capable of solving. We argue that LLM abstention is not only an expression of genuine uncertainty; it is also an artifact that can be largely influenced by prompts. We name this phenomenon *Abstention Inflation*. We add "Unknown" as an extra option for LLMs to choose from; experiments show serious accuracy drops on True/False Questions (TFQs). Replacing "Unknown" with an unrelated random word produces an identical effect. We argue that LLMs are trained to imitate the surface pattern of *abstention*, rather than to express genuine uncertainty. Based on eleven experimental settings, we support four claims that form a progressive argument: **(C1)** *Abstention Inflation* is triggered by the structural presence of an extra option, not by genuine uncertainty; **(C2)** further, it makes the model deny it can answer even when it can; **(C3)** at the representation level, this manifests as a later-layer output override; **(C4)** finally, this bias is stable across repeated sampling and option positions, emerges through instruction tuning, and is mitigated at larger model sizes.

cs.CL↗

arXiv2026

Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms

Large Language Models (LLMs) annotated datasets are widely used nowadays, however, large-scale annotations often show biases in low-quality datasets. For example, Multiple-Choice Questions (MCQs) datasets with one single correct option is common, however, there may be questions attributed to none or multiple correct options; whereas true-or-false questions are supposed to be labeled with either True or False, but similarly the text can include unsolvable elements, which should be further labeled as Unknown. There are problems when low-quality datasets with mixed question forms can not be identified. We refer to these exceptional label forms as Sparse Labels, and LLMs' ability to distinguish datasets with Sparse Labels mixture is important. Since users may not know situations of datasets, their instructions can be biased. To study how different instruction settings affect LLMs' identifications of Sparse Labels mixture, we introduce the concept of Instruction Boundary, which systematically evaluates different instruction settings that lead to biases. We propose BiasDetector, a diagnostic benchmark to systematically evaluate LLMs on datasets with mixed question forms under Instruction Boundary settings. Experiments show that users' instructions induce large biases on our benchmark, highlighting the need not only for LLM developers to recognize risks of LLM biased annotation resulting in Sparse Labels mixture, but also problems arising from users' instructions to identify them. Code, datasets and detailed implementations are available at https://github.com/ZpLing/Instruction-Boundary.

cs.CL↗