SOURCE-LINKED INTELLIGENCE

Prompt-Robust Language Models: Which Training Strategies Work?

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Despite their strong performance, large language models remain highly sensitive to prompt formulation. Prior work addresses this through refined data construction or through dedicated robustness objectives. We reproduce and compare these strategies under controlled conditions, and measure how effective they are in addressing models' prompt sensitivity. We find the current robustness fine-tuning methods improve over standard fine-tuning and in-context learning, but the best-to-worst prompt gap remains as high as 40-57% of performance. Moreover, the recent robustness-enhancing methods we test -

Read original source ↗ Open in workspace

recordType

paper

region

Global