做LLM评估或裁判定制的团队，这篇论文点出了多目标优化时容易踩的坑——梯度稀释和指令干扰，看完能帮你避开无效的提示优化策略。
该论文研究了在多评估标准下同时优化LLM裁判提示时出现的失败模式。由于文本梯度方法产生自然语言评论而非数值向量，多任务学习中的冲突解决工具（如PCGrad、MGDA）无法直接应用。实验测试了五种文本梯度优化器的分解模式，发现在10种配置中有6种优化效果未超过初始提示。当梯度LLM联合处理多个标准时，梯度特异性下降59%（从9.0降至3.7）。此外，简单合并各任务指令会导致斯皮尔曼相关系数下降5.3%。研究识别出两种可分离的失败模式：优化时的梯度稀释和推理时的指令干扰，这限制了多目标裁判定制的设计空间。
When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges
Customizing an LLM judge to a specific task or domain often involves optimizing its prompt across multiple evaluation criteria simultaneously. Textual gradient methods automate this for a single judge criterion, however they produce natural-language critiques, not numerical vectors. Thus, the conflict-resolution toolkit of multi-task learning (PCGrad, MGDA) doesn't apply to the multi-objective textual gradient setting. We test five decomposition modes of textual gradient optimizers by varying how much cross-task information the loss, gradient and optimizer LLMs share. In 6 of 10 configurations, we observe that optimization never improves over the initial prompt. Gradient specificity drops by 59% (from 9.0 to 3.7) when the gradient LLM processes multiple criteria jointly. Separately, we observe that naively combining per-task instructions into a single prompt degrades Spearman's rho by -5.3%. These results identify two separable failure modes: optimization-time gradient dilution and inference-time instruction interference, which together constrain the design space for multi-objective judge customization using textual feedback.