Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models
Abstract
Foundation models capable of generalizing across species and tasks represent a promising new frontier in bioacoustics, with NatureLM being one of the most prominent examples. While its domain-specific fine-tuning yields strong performance on bioacoustic benchmarks, we observe that it also introduces trade-offs in instruction-following flexibility. For instance, NatureLM achieves high accuracy when prompted for either the common or scientific name individually, but its accuracy drops significantly when both are requested in a single prompt. We address this by applying a simple model merging strategy that interpolates NatureLM with its base language model, recovering instruction-following capabilities with minimal loss of domain expertise. Finally, we show that the merged model exhibits markedly stronger zero-shot generalization, achieving over a 200% relative improvement and setting a new state-of-the-art in closed-set zero-shot classification of unseen species.
Davide Marincione
PhD Student
Donato Crisostomi
PostDoctoral Researcher
My research interests revolve around artificial intelligence, in particular mechanistic interpretability, model merging and representational alignment.
Emanuele Rodolà
Full Professor
