@inproceedings{liu-etal-2026-bigger,
    title = "A Bigger Catch: Fine-Grained Curriculum Standards Alignment on the {M}ath{F}ish Benchmark",
    author = "Liu, Xinman  and
      Sharma, Mayank  and
      Shi, Xinyu",
    editor = "Kochmar, Ekaterina  and
      Alhafni, Bashar  and
      Bann{\`o}, Stefano  and
      Bexte, Marie  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Tack, Anais  and
      Yaneva, Victoria  and
      Yuan, Zheng",
    booktitle = "Proceedings of the 21st Workshop on Innovative Use of {NLP} for Building Educational Applications ({BEA} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bea-1.15/",
    pages = "208--220",
    ISBN = "979-8-89176-409-5",
    abstract = "Most existing math benchmarks for LLMs focus on evaluating whether models produce correct solutions. In educational settings, however, it is equally important to understand whether LLMs grasp the pedagogical intent behind math problems, beyond simply arriving at the right answer. Tagging curriculum standards is challenging for the same reason: distinguishing fine-grained standards requires understanding subtle pedagogical distinctions. In this paper, we use the MathFish benchmark, which frames curriculum alignment as a multi-label prediction task over 385 Common Core State Standards, to evaluate a three-stage pipeline inspired by observed failure modes in retrieval and structural reasoning: curriculum-informed hard negatives (M1), a cross-encoder reranker (M2), and a ReAct agent paired with an LLM-as-a-judge critic (M3). We additionally evaluate a training-free alternative (A1) that combines hybrid sparse-dense retrieval with curriculum-graph reranking. M3 achieves 31.3{\%} exact-match accuracy, approximately 6.5{\texttimes} higher than the three-shot GPT-4-Turbo baseline. Error analysis shows that, despite these improvements, the pipeline still struggles with missing predictions, grade-level misalignment, and sibling-standard confusion, reinforcing that precise curriculum alignment remains a fundamentally difficult problem in educational NLP."
}