Abstract

"Recent advances in large-scale pre-training have substantially enhanced the robustness and generalization capabilities of foundation models (e.g., Qwen3 and Llama-4). However, when fine-tuning them on downstream tasks, these models often latch onto dataset-specific biases, learning spurious correlations tied to easy-to-learn but non-robust features. This undermines their performance under distribution shifts, despite strong in-distribution (ID) accuracy. Existing fine-tuning methods, including full-parameter and parameter-efficient techniques, primarily optimize for ID performance and largely overlook out-of-distribution (OOD) robustness. Meanwhile, debiasing has been explored in full fine-tuning, while debiasing strategies on Parameter-Efficient Fine-Tuning (PEFT) remain underexplored. To this end, in this paper, we propose Enhanced Debiased Gradient Extraction (EDGE), a lightweight gradient projection-based method that explicitly suppresses bias-amplifying updates during fine-tuning process. EDGE is a model-agnostic, and plug-and-play debiasing method that operates without relying on predefined bias types or labels.It seamlessly integrates with both full and parameter-efficient fine-tuning, and generalizes acrossNLP and vision tasks. Experiments on synthetic and real-world benchmarks demonstrate thatEDGE effectively reduces bias and consistently improves OOD generalization, offering a unified and practical framework for robust adaptation under dataset bias."