cs.AINov 12, 2026

Safety as a Budget: Calibrating the Control Channel of Constrained GRPO for Vision-Language Models

Authors: Bo Han

Abstract

Reinforcement learning can teach vision-language models (VLMs) to decline harmful image-text requests, but how safe the result becomes is set indirectly, through reward weights found by trial runs. Stating safety as budgets on the rate of harmful assistance and the rate of over-refusal, enforced by Lagrange multipliers inside GRPO with an off-the-shelf scorer as the cost, is the natural fix, and it fails twice. The multiplier compares the scorer's mean with the budget, and scorers built for ranking get the mean wrong: a fixed-point analysis shows that the mean bias, not the budget, then decides whether the multiplier settles, saturates or switches off. And standard GRPO standardizes the penalized reward within each group, which cancels the multiplier before it reaches the gradient. Two-channel constrained GRPO repairs both: the base reward keeps the raw score for the within-group comparison, the penalty and the constraint estimate pass through a monotone map fitted on judge-labeled training responses, and the advantage keeps the multiplier. On a Qwen3-VL-2B policy with a training-free readout of an open 4B model as the scorer, held-out harm on 1,037 adversarial prompts falls from 8.9% under standard GRPO to 4.8%, lower in every seed, where the uncalibrated budget gives 7.6%; over-refusal stays at most 2% on 400 benign queries and MMBench is unchanged. The gain is largest where the intent sits in the image (10.1% -> 5.1%) and grows on the unseen HADES benchmark (28.9% -> 12.8%). Order-preserving distortions of the scores reproduce each predicted controller state in every seed, and the results hold under a map fitted on another judge's labels, an image-reading judge and a human audit.

Figures & tables

Explore similar work

Oct 5, 2026

Visual Grounding Safety in Vision-Language Models

Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes that downstream interfaces, agents, and robots can act on, yet safety alignment of this output channel has not been systematically analyzed. We study visual grounding safety by repurposing three safety benchmarks spanning direct harm (VLSU), social bias (BBQ-V), and situational safety (Asimov-2.0) into 15,401 matched pairs of harmful requests that differ only in the requested output: a free-text answer (VQA) or a grounding (point or bounding box). Across five VLMs, models that refuse a harmful request posed as a question often comply when the same request asks for a grounding: averaged over models, grounding refusal trails VQA refusal by 31-59 percentage points, depending on the domain, and safety system prompts do not close this gap. We propose a fine-tuning approach that combines grounding-form refusals with capability grounding data and self-distilled benign data to counter over-refusal. For Qwen3-VL-8B and VisionReasoner-7B, it improves grounding refusal by 77-95 percentage points on VLSU and BBQ-V and by 64-85 points on the held-out Asimov-2.0 domain, while also improving VQA refusal, preserving grounding capability, and keeping over-refusal limited. Representation analysis shows that fine-tuning moves harmful requests toward each model's refusal direction, most strongly for grounding, while leaving benign requests near the harmless reference.
Sep 29, 2026

Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment

Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly elicit unsafe responses. Existing safety methods often require large preference datasets, costly multi-rollout training, or additional safeguards at inference time. They may also sacrifice helpfulness by directly refusing requests that could be answered safely. In this paper, we propose Intent-Privilege On-Policy Self-Distillation (OPSD), which leverages evidence-grounded intent as privileged supervision during training to help VLMs recognize implicit risks and provide safe, useful responses instead of blanket refusals. OPSD distills a teacher's intent-conditioned preferences over responses into a student using a single rollout per prompt; the student then responds without intent annotations or an additional safety module. With only 1,447 safety-specific examples - 95% fewer than standard preference datasets - OPSD reduces training time by 5x relative to multi-rollout GRPO-style training and average inference length by 7%. It attains the highest ratio for joint safety-helpfulness success, which measures the proportion of responses that are both safe and helpful, across all five evaluation groups. Remarkably, on pooled SIUO+HoliSafe, this success ratio rises from 43.9% to 53.5%. These results show that training-time intent supervision can improve both safety and helpfulness while substantially reducing data, training, and inference costs.
Aug 21, 2026

Perturb the Thought, Not the Pixels: Latent-Space Rollout Diversification for Reinforcement Learning of Vision-Language Models

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning ability of vision-language models (VLMs), and diversifying the rollouts within each optimization group amplifies its gains. Existing approaches diversify through decoding temperature or pixel-space image distortion; we ask whether the perturbation belongs in the model's latent space instead. We introduce Noise-Contrastive GRPO (NC-GRPO), which injects scale-calibrated Gaussian noise into the last hidden layer of the prompt-encoding pass for half of each rollout group, branching those rollouts from a displaced departure state. Branches that reach the answer despite the displacement are reinforced over those derailed by it, converting sensitivity at the branch point into policy-gradient signal; the objective, reward, and inference protocol are untouched. On Qwen2.5-VL-7B trained on Geometry3K, NC-GRPO significantly improves out-of-domain mathematical reasoning over vanilla GRPO across five held-out benchmarks (pooled McNemar p≤0.001p \le 0.001) while also improving in-domain accuracy and hallucination robustness -- the latter an axis on which image-space noise regresses even while posting a larger OOD average on perception-heavy benchmarks. Mechanism ablations indicate that independent stochastic diversity, not noise budget or direction, is the active ingredient, and a noise-scale study exposes a dial between reasoning specialization and general capability. NC-GRPO is designed to be modality-agnostic and integrates into a standard RLVR pipeline as a ~50-line change to the inference engine.