When AI tools can generate many solutions, some human preference must be applied to determine which solution is relevant to the current project. One way to find those preferences is interactive search-based software engineering (iSBSE) where humans can influence the search process. Current iSBSE methods can lead to cognitive fatigue (when they overwhelm humans with too many overly elaborate questions). WHUN is an iSBSE algorithm that avoids that problem. Due to its recursive clustering procedure, WHUN only pesters humans for $O(log_2{N})$ interactions. Further, each interaction is mediated via a feature selection procedure that reduces the number of asked questions. When compared to prior state-of-the-art iSBSE systems, WHUN runs faster, asks fewer questions, and achieves better solutions that are within $0.1\%$ of the best solutions seen in our sample space. More importantly, WHUN scales to large problems (in our experiments, models with 1000 variables can be explored with half a dozen interactions where, each time, we ask only four questions). Accordingly, we recommend WHUN as a baseline against which future iSBSE work should be compared. To facilitate that, all our scripts are online at https://github.com/ai-se/whun.

中文翻译：

---

大型产品线中的偏好发现

当 AI 工具可以生成许多解决方案时，必须应用一些人类偏好来确定哪个解决方案与当前项目相关。找到这些偏好的一种方法是基于交互式搜索的软件工程 (iSBSE)，人类可以在其中影响搜索过程。当前的 iSBSE 方法会导致认知疲劳（当它们用太多过于复杂的问题压倒人类时）。WHUN 是一种避免该问题的 iSBSE 算法。由于其递归聚类过程，WHUN 仅针对 $O(log_2{N})$ 交互来纠缠人类。此外，每个交互都通过一个特征选择过程进行调解，该过程减少了被问到的问题的数量。与之前最先进的 iSBSE 系统相比，WHUN 运行速度更快，提出的问题更少，并实现了成本在 0 美元以内的更好的解决方案。在我们的示例空间中看到的最佳解决方案的 1\%$。更重要的是，WHUN 可以扩展到大问题（在我们的实验中，可以通过六个交互来探索具有 1000 个变量的模型，其中每次我们只问四个问题）。因此，我们建议将 WHUN 作为基准，用于比较未来的 iSBSE 工作。为方便起见，我们所有的脚本都在 https://github.com/ai-se/whun 在线。