用检索结果直接答监管题，靠关键词拼接刷出高分，再优化生成更靠谱答案。
AUEB-Archimedes at RIRAG-2025: Is obligation concatenation really all you need?
- 用三模型检索+重排序，从文本中提取关键义务句提升得分。
- 直接拼接义务句得0.947分，但答案不连贯；优化后得0.639分更合理。
- 适合关注评估漏洞与可读性生成的NLP研究者。
本文介绍我们为RIRAG-2025设计的系统，该任务要求通过检索相关段落来回答监管类问题。答案采用RePASs（一种无参考、基于模型的评估指标）进行评测。我们的系统结合了三种检索模型与一个重排序器。我们发现，利用RePASs中提取重要句子（即‘义务’）的神经组件，即使直接从检索结果中摘取答案，也能获得极高的分数（0.947）。随后，我们通过在多个生成候选答案中选择最优的RePASs分数，并迭代减少矛盾、覆盖更多义务，生成了可读性强且连贯的答案，最终取得更合理且较高的分数（0.639）。
原文摘要 · Abstract (English)
This paper presents the systems we developed for RIRAG-2025, a shared task that requires answering regulatory questions by retrieving relevant passages. The generated answers are evaluated using RePASs, a reference-free and model-based metric. Our systems use a combination of three retrieval models and a reranker. We show that by exploiting a neural component of RePASs that extracts important sentences ('obligations') from the retrieved passages, we achieve a dubiously high score (0.947), even though the answers are directly extracted from the retrieved passages and are not actually generated answers. We then show that by selecting the answer with the best RePASs among a few generated alternatives and then iteratively refining this answer by reducing contradictions and covering more obligations, we can generate readable, coherent answers that achieve a more plausible and relatively high score (0.639).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。