Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models

arXiv:2610.10526v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-language models they are built on. A one-word edit can move success by tens of points: pi_{0.5} turns on a LIBERO stove 100% of the time for "switch on the stove" and 2% for "switch on the hot plate", and a pi_0 checkpoint finetuned with rephrase augmentation still shows swings of up to 61 points. We characterize this sensitivity with statistically tested single-edit swings and an oracle phrase search, which shows that phrasing alone nearly closes the 21-point gap between in-distribution and out-of-distribution tasks. We then reduce it without modifying the policy. Because the sensitivity is systematic, it can be expressed as explicit rules: we score many phrasings of a few training tasks, have a large language model distill the evidence into ten to twenty rephrasing rules, and at deployment rewrite each incoming instruction once under these rules. The rules improve the frozen pi_0 by 16 to 27% relative on twelve held-out tasks across adversarial, VLM-generated, and human-generated phrasings, with gains concentrated on out-of-distribution tasks. The pipeline replicates on pi_{0.5} and LIBERO, lifting in-finetune success from 93.6% to 97.8%. The method requires no retraining and no per-step verification, and applies zero-shot to unseen tasks and instructions. Project website: https://sttawm.github.io/rephrase-before-you-act

Related

• Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations
• MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language Models
• When Safety Overrides Vision: Exploring Dynamics between Vision Influence and Safety Alignment in Vision-Language Models

Source: arXiv cs.CL | 2026-10-08