AI 中文总结
本文提出多维比较量表构建框架，通过成对比较与稀疏Elo优化降低成本，并推出SubJudge模型实现个性化评分的O(1)推理，在多项指标上媲美前沿大模型。
AI 中文摘要
主观判断在许多高流量应用中处于核心地位，但主观强度难以量化，且不同个体之间的感知差异显著。为应对这些挑战，我们提出了一种用于多维量表构建的成对比较框架。通过沿案例维度和画像维度比较案例-个体对，该框架构建出能够同时捕捉细粒度强度和个体差异的相对量表。为支持实际的高流量部署，我们优化了离线量表构建和在线推理两个环节。在量表构建方面，我们将稀疏Elo比较与多裁判投票相结合，对于N个对象和每个对象K个对手的预算，将比较成本从O(N^2)降至O(NK)，同时限制对任何单一裁判的依赖。在推理方面，我们提出了SubJudge，一个用于个性化评分的System One模型，采用批量偏好优化（BPO）。利用Bradley-Terry比较，BPO训练模型学习相对排序，SubJudge从首个响应位置的数字令牌概率中读取连续分数，每个标准仅需一次前向传播，将推理复杂度降至O(1)。在PluriHarms和iNews上的实验表明，我们的9B模型在多项指标上达到或超越了所评估的前沿LLM。在H100 GPU上，与不同思考预算下的Qwen3.5-9B相比，SubJudge的平均推理延迟实现了约1.29倍至261倍的加速。代码可在该https URL获取。
英文摘要
Subjective judgments are central to many high-traffic applications, but subjective intensity is difficult to quantify and perceptions vary substantially across individuals. To address these challenges, we propose a pairwise comparative framework for multi-dimensional scale construction. By comparing case-person pairs along case and profile dimensions, the framework constructs relative scales that capture both fine-grained intensity and individual variation. To support practical high-traffic deployment, we optimize both offline scale construction and online inference. For scale construction, we combine sparse Elo comparisons with multi-judge voting, cutting the comparison cost from $O(N^2)$ to $O(NK)$ for $N$ objects and a budget of $K$ opponents per object, while limiting reliance on any single judge. For inference, we propose SubJudge, a System One model for personalized scoring with Batchwise Preference Optimization (BPO). Using Bradley-Terry comparisons, BPO trains the model to learn relative orderings, and SubJudge reads a continuous score from digit-token probabilities at the first response position, requiring only one forward pass per criterion and reducing the inference complexity to $O(1)$. Experiments on PluriHarms and iNews show that our 9B models match or surpass the evaluated frontier LLMs on multiple metrics. On the H100 GPU, SubJudge achieves an approximately $1.29\times$ to $261\times$ speedup in mean inference latency over Qwen3.5-9B with different thinking budgets. The code is available at https://github.com/Longchentong/SubJudge.
