CLMar 19, 2025

Unified Enhancement of the Generalization and Robustness of Language Models via Bi-Stage Optimization

arXiv:2503.16550v1h-index: 2
Originality Highly original
AI Analysis

It addresses the problem of developing robust and generalized language models for AI applications, presenting a novel approach rather than an incremental improvement.

The paper tackles the challenge of simultaneously improving generalization and robustness in language models by proposing a bi-stage optimization framework, achieving state-of-the-art performance across 13 datasets.

Neural network language models (LMs) are confronted with significant challenges in generalization and robustness. Currently, many studies focus on improving either generalization or robustness in isolation, without methods addressing both aspects simultaneously, which presents a significant challenge in developing LMs that are both robust and generalized. In this paper, we propose a bi-stage optimization framework to uniformly enhance both the generalization and robustness of LMs, termed UEGR. Specifically, during the forward propagation stage, we enrich the output probability distributions of adversarial samples by adaptive dropout to generate diverse sub models, and incorporate JS divergence and adversarial losses of these output distributions to reinforce output stability. During backward propagation stage, we compute parameter saliency scores and selectively update only the most critical parameters to minimize unnecessary deviations and consolidate the model's resilience. Theoretical analysis shows that our framework includes gradient regularization to limit the model's sensitivity to input perturbations and selective parameter updates to flatten the loss landscape, thus improving both generalization and robustness. The experimental results show that our method significantly improves the generalization and robustness of LMs compared to other existing methods across 13 publicly available language datasets, achieving state-of-the-art (SOTA) performance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes