针对多语言金融问答，提出语言感知的检索与评分系统。
Language-Routed RAG and Direct Option Scoring for Multilingual Financial QA: DS@GT at FinMMEval
- 按查询语言自动路由模型，用双索引融合提升低资源语言检索效果。
- 通过直接选项打分（RADS）获取答案，准确率在中文上达90.7%。
- 发现思维链提示会严重降低希腊语和阿拉伯语表现，需谨慎使用。
我们提交DS@GT参与FinMMEval 2026任务1，该任务为涵盖英语、西班牙语、希腊语、中文和印地语的多语言金融问答基准。金融认证考试如CFA、EFPA和CPA要求结构化领域推理，而现有NLP基准难以捕捉此类能力，且跨语言时检索与表示基础设施薄弱。我们在LangGraph上构建了检索增强管道：检测查询语言，利用BGE-M3嵌入与FAISS索引从30,209条多语言知识库中检索语义相关示例。系统采用检索增强直接评分（RADS），通过候选选项字母的下一个词符概率进行打分，而非生成自由文本。对于低资源语言，采用加权倒数排名融合（RRF）融合单语言与跨语言检索索引。模型选择按语言路由：阿拉伯语、中文和印地语用Qwen3-14B；英语用Qwen2.5-14B；希腊语用Llama-3.1-8B，此路由基于实证消融实验得出，揭示显著的语言性能差异。值得注意的是，链式思维提示使希腊语准确率从90.7%降至20.9%，开启Qwen3默认思考模式则使阿拉伯语RADS性能跌至近随机水平。结果表明，有效多语言金融推理需语言感知的检索、模型路由与评分策略选择。
原文摘要 · Abstract (English)
We present DS@GT's submission to FinMMEval 2026 Task 1, a multilingual financial exam question answering benchmark spanning English, Spanish, Greek, Chinese, and Hindi. Financial certification exams such as the CFA, EFPA, and CPA demand structured domain reasoning that standard NLP benchmarks do not capture, and this challenge compounds across languages where retrieval and representation infrastructure is underdeveloped. We build a retrieval-augmented pipeline on LangGraph that detects query language and retrieves semantically relevant exemplars from a 30,209-entry multilingual knowledge base using BGE-M3 embeddings and FAISS indexing. The system then scores answers via Retrieval-Augmented Direct Scoring (RADS), reading next-token log-probabilities over candidate option letters rather than generating free-form output. For low-resource languages, we fuse per-language and cross-lingual retrieval indices using weighted Reciprocal Rank Fusion. Model selection is language-routed: Qwen3-14B for Arabic, Chinese, and Hindi; Qwen2.5-14B for English; and Llama-3.1-8B for Greek, a routing derived from empirical ablations that reveal substantial language-asymmetric performance gaps. Notably, chain-of-thought prompting significantly degrades Greek accuracy (90.7% to 20.9%), and enabling Qwen3's default thinking mode collapses Arabic RADS performance to near-chance levels. Our results indicate that effective multilingual financial reasoning requires language-aware retrieval, model routing, and deliberate scoring strategy selection.
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。