Probing and Steering Uncertainty in Biomedical Language Models: Representational Structure and Behavioral Limits
Year: 2026
Type: conference-paper
Abstract: Biomedical language models can generate overly confident clinical statements despite incomplete or ambiguous evidence.We study whether linguistic uncertainty (the hedged epistemic stance expressed in phrases such as "consistent with" or "cannot exclude") is encoded in model representations and can be controlled without retraining.Across six biomedical language models spanning two architectures (causal decoders and bidirectional encoders), we show that uncertainty is captured by robust low-dimensional linear structure in hidden states.We then apply activation steering to manipulate this representation directly, increasing hedged generation in decoder models and inducing targeted uncertainty-related shifts in encoder representations.Together, these results show that epistemic stance is not merely a surface linguistic phenomenon but an interpretable and controllable feature of biomedical language model representations, with implications for safer and more calibrated clinical text generation.
Author: Debmalya Pal
Institution: University of California San Diego
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W7166823489