从稀疏决策到密集推理：一种多属性轨迹范式用于多模态调制
From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation
AI总结：
UniMod提出一种多属性轨迹范式，通过多维边界学习提升多模态调制效果，以更少的数据实现高效安全内容识别。
摘要：
安全调制对于识别有害内容至关重要。尽管文本安全调制取得了成功，但其多模态对应物仍受到数据和监督双重稀疏性的阻碍。传统依赖二元标签会导致捷径学习，这会掩盖有效多模态区分所需的内在分类边界。因此，我们提出了一种新的学习范式（UniMod），从稀疏决策转向密集推理轨迹。通过构建涵盖证据接地、模态评估、风险映射、政策决策和响应生成的结构化轨迹，我们将单体决策任务改造成多维边界学习过程。这种方法迫使模型在显式的安全语义上做出决策，防止模型收敛到表面的捷径。为了促进这一范式，我们开发了一个多头标量奖励模型（UniRM）。UniRM通过在响应生成阶段为属性级分配评分提供多维监督。此外，我们引入了专门的优化策略，以解耦任务特定参数并重新平衡训练动态，有效解决了多任务学习中不同目标之间的干扰。实验结果表明，UniMod在文本调制性能上具有竞争力，并在少于领先基线所用训练数据40%的情况下设定了多模态基准。消融进一步验证了我们的多属性轨迹推理，提供了一个有效且高效的多模态调制框架。补充材料可在项目网站https://trustworthylab.github.io/UniMod/上获取。
英文摘要：
Safety moderation is pivotal for identifying harmful content. Despite the success of textual safety moderation, its multimodal counterparts remain hindered by a dual sparsity of data and supervision. Conventional reliance on binary labels lead to shortcut learning, which obscures the intrinsic classification boundaries necessary for effective multimodal discrimination. Hence, we propose a novel learning paradigm (UniMod) that transitions from sparse decision-making to dense reasoning traces. By constructing structured trajectories encompassing evidence grounding, modality assessment, risk mapping, policy decision, and response generation, we reformulate monolithic decision tasks into a multi-dimensional boundary learning process. This approach forces the model to ground its decision in explicit safety semantics, preventing the model from converging on superficial shortcuts. To facilitate this paradigm, we develop a multi-head scalar reward model (UniRM). UniRM provides multi-dimensional supervision by assigning attribute-level scores to the response generation stage. Furthermore, we introduce specialized optimization strategies to decouple task-specific parameters and rebalance training dynamics, effectively resolving interference between diverse objectives in multi-task learning. Empirical results show UniMod achieves competitive textual moderation performance and sets a new multimodal benchmark using less than 40\% of the training data used by leading baselines. Ablations further validate our multi-attribute trajectory reasoning, offering an effective and efficient framework for multimodal moderation. Supplementary materials are available at \href{https://trustworthylab.github.io/UniMod/}{project website}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
