EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment
This work addresses the economic efficiency and safety trade-off in LVLM alignment, offering a principled solution for robust deployment, though it appears incremental as it builds on existing alignment concepts with a novel economic framing.
The paper tackles the problem of aligning Large Vision-Language Models (LVLMs) by addressing jailbreak vulnerabilities and inefficiencies in current methods, proposing EcoAlign as an inference-time framework that reframes alignment as an economically rational search. Results show EcoAlign matches or surpasses state-of-the-art safety and utility at lower computational cost across multiple models and datasets.
Large Vision-Language Models (LVLMs) exhibit powerful reasoning capabilities but suffer sophisticated jailbreak vulnerabilities. Fundamentally, aligning LVLMs is not just a safety challenge but a problem of economic efficiency. Current alignment methods struggle with the trade-off between safety, utility, and operational costs. Critically, a focus solely on final outputs (process-blindness) wastes significant computational budget on unsafe deliberation. This flaw allows harmful reasoning to be disguised with benign justifications, thereby circumventing simple additive safety scores. To address this, we propose EcoAlign, an inference-time framework that reframes alignment as an economically rational search by treating the LVLM as a boundedly rational agent. EcoAlign incrementally expands a thought graph and scores actions using a forward-looking function (analogous to net present value) that dynamically weighs expected safety, utility, and cost against the remaining budget. To prevent deception, path safety is enforced via the weakest-link principle. Extensive experiments across 3 closed-source and 2 open-source models on 6 datasets show that EcoAlign matches or surpasses state-of-the-art safety and utility at a lower computational cost, thereby offering a principled, economical pathway to robust LVLM alignment.