用现成模型实现乌克兰多领域文档理解，精准定位答案来源
Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
- 按上下文切分PDF，结合问题与选项重排候选段落
- 重排后使用前2段提升答案准确率至96.74%
- 适合需快速部署、重视结构保留的文档问答任务
我们参加了第五届UNLP多领域文档理解共享任务，要求从PDF集合中回答乌克兰语多项选择题，并定位支持答案的文档和页码。提出一种基于三方面改进的检索增强流水线：对PDF进行上下文感知切块，利用问题感知密集检索与结合问题和选项的重排机制，以及基于有限重排段落的约束式答案生成。最终系统采用Qwen3-Embedding-8B进行检索，微调后的Qwen3-Reranker-8B进行段落排序，Qwen3-32B进行答案选择。在保留测试集上，重排使Recall@1从0.6957提升至0.7935；使用前2个重排段落后，答案准确率从0.9348升至0.9674。最佳公开榜单得分0.9452，私有榜单得分0.9598。结果表明，在严格代码竞赛限制下，保持文档结构并让相关性判断关注答案空间，比添加复杂下游启发式更有效。
原文摘要 · Abstract (English)
We participated in the Fifth UNLP shared task on multi-domain document understanding, where systems must answer Ukrainian multiple-choice questions from PDF collections and localize the supporting document and page. We propose a retrieval-augmented pipeline built around three ideas: contextual chunking of PDFs, question-aware dense retrieval and reranking conditioned on both the question and answer options, and constrained answer generation from a small set of reranked passages. Our final system uses Qwen3-Embedding-8B for retrieval, a fine-tuned Qwen3-Reranker-8B for passage ranking, and Qwen3-32B for answer selection. On a held-out split, reranking improves Recall@1 from 0.6957 to 0.7935, while using the top-2 reranked passages raises answer accuracy from 0.9348 to 0.9674. Our best leaderboard run reached 0.9452 on the public leaderboard and 0.9598 on the private leaderboard. Our results suggest that, under strict code-competition constraints, preserving document structure and making relevance estimation aware of the answer space are more effective than adding complex downstream heuristics.
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。