AI 中文总结
本研究针对学术导师发现任务，对比评估六种检索方法，基于768名美高校CS教师档案数据，发现Reranked方法表现最优，还揭示了不同信息类型对检索效果的影响并公开了全部相关资源。
AI 中文摘要
我们针对学术导师发现任务开展了六种信息检索方法的对比评估：即根据研究生申请者的研究兴趣陈述对计算机科学（CS）教师进行相关性排名。所评估的方法涵盖稀疏词汇匹配（Jaccard重叠、TF-IDF、BM25）、密集语义检索（all-MiniLM-L6-v2句子嵌入）、混合分数融合以及学习排序。评估采用了一个新的领域特定数据集：从美国9所高校计算机科学系爬取的768份教师档案，包含针对5个代表不同研究生研究概况的查询的162个分级相关性判断（等级0/1/2）。在所有5个查询中，Reranked方法获得最高的平均NDCG@10（0.477，标准差0.138），其次是Semantic（0.450）、Hybrid（0.421）、BM25（0.406）、Jaccard（0.303）和TF-IDF（0.246）。在所有15组两两比较经Bonferroni校正后，TF-IDF的表现显著差于BM25、Semantic、Hybrid和Reranked；其余两两差异在5个查询的校正后均不显著。领域 ablation分析显示，仅个人简介（NDCG 0.634）的表现优于结合个人简介与研究领域标签的完整模型（0.593）。对照实验表明，拼接arXiv论文摘要会使NDCG@10降低0.176，这为晚融合架构提供了动机。所有代码、爬虫工具及相关性标签均已公开发布。
英文摘要
We present a comparative evaluation of six information retrieval methods for the task of academic advisor discovery: ranking CS faculty members by relevance to a graduate applicant's research interest statement. The methods span sparse lexical matching (Jaccard overlap, TF-IDF, BM25), dense semantic retrieval (all-MiniLM-L6-v2 sentence embeddings), hybrid score fusion, and learning-to-rank. Evaluation uses a new domain-specific collection: 768 faculty profiles scraped from 9 US CS departments, with 162 graded relevance judgments (grade 0/1/2) across 5 queries representing distinct graduate student research profiles. Across all five queries, Reranked achieves the highest mean NDCG@10 (0.477, std 0.138), followed by Semantic (0.450), Hybrid (0.421), BM25 (0.406), Jaccard (0.303), and TF-IDF (0.246). After Bonferroni correction across all 15 pairwise comparisons, TF-IDF is significantly worse than BM25, Semantic, Hybrid, and Reranked; no other pairwise difference survives correction at 5 queries. A field ablation reveals that biography alone (NDCG 0.634) outperforms the full model combining biography with research area tags (0.593). A controlled experiment shows that concatenating arXiv paper abstracts reduces NDCG@10 by 0.176, motivating a late-fusion architecture. All code, scrapers, and relevance labels are released openly.
Comments16 pages, 2 figures, 9 tables. Code and demo at https://github.com/subedibiraj/academic-discovery
