Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs

• URL: http://arxiv.org/abs/2603.13292v1
• Date: Sat, 28 Feb 2026 08:29:29 GMT
• Title: Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs
• Abstract summary: Multimodal Large Language Models (MLLMs) pose critical safety challenges.<n>Current methods often face a safety-utility trade-off: they either refuse benign queries out of excessive caution or overlook latent risks in cross-modal interactions.<n>We introduce Pragma-VL, an end-to-end alignment algorithm that enables MLLMs to pragmatically arbitrate between safety and helpfulness.
• Score: 23.5028441939688
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal safety alignment via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is a primary mitigation strategy, current methods often face a safety-utility trade-off: they either refuse benign queries out of excessive caution or overlook latent risks in cross-modal interactions. To resolve this, we introduce Pragma-VL, an end-to-end alignment algorithm that enables MLLMs to pragmatically arbitrate between safety and helpfulness. First, we enhance visual risk perception with a novel cold-start SFT stage. This is achieved by applying risk-aware clustering to the visual encoder and using an interleaved dataset of risk descriptions and high-quality data. Second, we introduce a theoretically-guaranteed reward model that leverages synergistic learning. We train it with a novel data augmentation method that assigns dynamic weights based on the queries, enabling contextual arbitration between safety and helpfulness. Extensive experiments show that Pragma-VL effectively balances safety and helpfulness, outperforming baselines by 5% to 20% on most multimodal safety benchmarks while preserving its general capabilities in areas such as mathematics and knowledge reasoning.

Related papers

• Investigating and Alleviating Harm Amplification in LLM Interactions [35.365004091470944]
  We introduce HarmAmp, a new benchmark for multi-turn harm amplification scenarios spanning twelve risk categories.<n>We propose TrajSafe, a proactive monitor that anticipates harmful trajectories and intervenes through probing users' genuine intents.
  arXiv  Detail & Related papers  (2026-06-01T16:01:37Z)
• Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming [64.48633529149579]
  We propose a novel framework to expose the vulnerabilities of Vision-Language-Action (VLA) models against linguistic variations.<n>Our method reduces the average task success rate from 93.33% to 5.85%, demonstrating a scalable approach to stress-testing VLA agents.
  arXiv  Detail & Related papers  (2026-04-07T08:43:36Z)
• Robust Multimodal Safety via Conditional Decoding [52.92816441364308]
  Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.<n>We propose a simple conditional decoding strategy, CASA, that utilizes internal representations of MLLMs to predict a binary safety token before response generation.
  arXiv  Detail & Related papers  (2026-03-31T23:19:50Z)
• Rethinking Safety in LLM Fine-tuning: An Optimization Perspective [56.31306558218838]
  We show that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts.<n>We propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance.<n>Our experiments on the Llama families across multiple datasets demonstrate that safety problems can largely be avoided without specialized interventions.
  arXiv  Detail & Related papers  (2025-08-17T23:46:36Z)
• SafeCoT: Improving VLM Safety with Minimal Reasoning [5.452721786714111]
  We introduce SafeCoT, a lightweight, interpretable framework to improve refusal behavior in vision-language models.<n>We show that SafeCoT significantly reduces overrefusal and enhances generalization, even with limited training data.
  arXiv  Detail & Related papers  (2025-06-10T03:13:50Z)
• Saffron-1: Safety Inference Scaling [69.61130284742353]
  SAFFRON is a novel inference scaling paradigm tailored explicitly for safety assurance.<n>Central to our approach is the introduction of a multifurcation reward model (MRM) that significantly reduces the required number of reward model evaluations.<n>We publicly release our trained multifurcation reward model (Saffron-1) and the accompanying token-level safety reward dataset (Safety4M)
  arXiv  Detail & Related papers  (2025-06-06T18:05:45Z)
• DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models [37.104276926258095]
  Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data.<n>We introduce textbfDREAM (textittextbfDisentangling textbfRisks to textbfEnhance Safety textbfAlignment in textbfMLLMs), a novel approach that enhances safety alignment in MLLMs through supervised fine-tuning and iterative Reinforcement Learning from AI Feedback.
  arXiv  Detail & Related papers  (2025-04-25T03:54:24Z)
• Representation Bending for Large Language Model Safety [27.842146980762934]
  Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks pose significant challenges.<n>This paper introduces RepBend, a novel approach that fundamentally disrupts the representations underlying harmful behaviors in LLMs.<n>RepBend achieves state-of-the-art performance, outperforming prior methods such as Circuit Breaker, RMU, and NPO, with up to 95% reduction in attack success rates.
  arXiv  Detail & Related papers  (2025-04-02T09:47:01Z)
• Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models [92.38300626647342]
  Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs.<n>This paper presents a theoretical framework for understanding the interplay between safety and capability in two primary safety-aware LLM fine-tuning strategies.
  arXiv  Detail & Related papers  (2025-03-24T20:41:57Z)
• Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback [34.01716144973483]
  Multimodal large language models (MLLMs) are essential for building general-purpose AI assistants.<n>How can we ensure safety alignment of MLLMs to prevent undesired behaviors?<n>In this work, we present the first exploration of the Safe RLHF-V -- the first multimodal safety alignment framework.
  arXiv  Detail & Related papers  (2025-03-22T07:40:20Z)
• Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models [94.39278422567955]
  Fine-tuning large language models (LLMs) on human preferences has proven successful in enhancing their capabilities.<n>However, ensuring the safety of LLMs during fine-tuning remains a critical concern.<n>We propose a supervised learning framework called Bi-Factorial Preference Optimization (BFPO) to address this issue.
  arXiv  Detail & Related papers  (2024-08-27T17:31:21Z)
• Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models? [2.089112028396727]
  This study explores whether Large Language Models can produce safe, unbiased outputs without sacrificing knowledge or comprehension.<n>We introduce the Safe and Responsible Large Language Model (textbfSR$_textLLM$)<n>Experiments on our specialized dataset and out-of-distribution test sets reveal that textbfSR$_textLLM$ effectively reduces biases while preserving knowledge integrity.
  arXiv  Detail & Related papers  (2024-04-01T18:10:05Z)
• RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [62.685566387625975]
  Current mitigation strategies, while effective, are not resilient under adversarial attacks. This paper introduces Resilient Guardrails for Large Language Models (RigorLLM), a novel framework designed to efficiently moderate harmful and unsafe inputs.
  arXiv  Detail & Related papers  (2024-03-19T07:25:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.