# MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs Source: [MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:25:22.107Z Authors: Yongqi Fan, Yating Wang, Guandong Wang, Jie Zhai, Jingping Liu, Qi Ye, Tong Ruan Published: 2025-06-18T07:49:13.000Z ## Abstract Open-ended question answering (QA) is a key task for evaluating the capabilities of large language models (LLMs). Compared to closed-ended QA, it demands longer answer statements, more nuanced reasoning processes, and diverse expressions, making refined and interpretable automatic evaluation both crucial and challenging. Traditional metrics like ROUGE and BERTScore struggle to capture semantic similarities due to different patterns between model responses and reference answers. Current LLM-based evaluation approaches, such as pairwise or listwise comparisons of candidate answers, lack intuitive interpretability. While pointwise scoring of each response provides some descriptions, it fails to adapt across different question contents. Most notably, existing methods overlook the distinction between factoid and non-factoid questions. To address these challenges, we propose \\textbf{MinosEval}, a novel evaluation method that first distinguishes open-ended questions and then ranks candidate answers using different evaluation strategies. For factoid questions, it applies an adaptive key-point scoring strategy, while for non-factoid questions, it uses an instance-aware listwise ranking strategy. Experiments on multiple open-ended QA datasets, including self-built ones with more candidate responses to complement community resources, show that MinosEval better aligns with human annotations and offers more interpretable results. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Open-ended Question Answering on ANTIQUE (S5)](): Open-ended Question Answering; ANTIQUE (S5); Kendall's Tau (K): 65.97. - [Open-ended Question Answering on TREC-DL-NF (S5)](): Open-ended Question Answering; TREC-DL-NF (S5); Kendall's Tau (K): 68.61. - [Open-ended QA Response Ranking on AlignBench Minos](): Open-ended QA Response Ranking; AlignBench Minos; K Score: 47.68. - [Open-ended QA Response Ranking on GaokaoBench Minos](): Open-ended QA Response Ranking; GaokaoBench Minos; K Score: 59.77. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()