Fungi exhibit diverse trophic strategies, ranging from obligate symbiosis to saprotrophy, with some taxa capable of occupying multiple ecological roles. Manually identifying trophic versatility from the literature is time-consuming and difficult to scale. Here, we present a pilot workflow that automates the classification of fungal trophic modes using BioBERT, a transformer-based language model applied to biomedical research papers. A curated dataset of 56 fungal ecology abstracts was manually labeled as dual (occupying multiple trophic modes) or solo (restricted to one mode) and used to fine-tune BioBERT for binary classification. The model achieved 86% accuracy with balanced precision and recall, demonstrating that machine learning can replicate literature-based trait assignments. This pilot study emphasizes reproducibility, transparency, and open data integration, offering a proof-of-concept for linking literature-derived ecological information to existing fungal trait databases such as FUNGuild and FungalTraits. All code, data, and trained models are openly available to support reuse and scaling to larger datasets.