用于多语言金融问答的语言路由RAG和直接选项评分：FinMMEval上的DS@GT
Language-Routed RAG and Direct Option Scoring for Multilingual Financial QA: DS@GT at FinMMEval
浏览论文内容
中文总结 AI 辅助
该研究针对多语言金融问答基准FinMMEval 2026任务1，构建基于LangGraph的检索增强管道，用RADS评分，通过加权倒数排名融合低资源语言索引，采用语言路由选择模型，揭示语言感知检索等对多语言金融推理的重要性。
中文摘要 AI 辅助
我们展示了DS@GT提交给2026年FinMMEval任务1的内容，这是一个涵盖英语、西班牙语、希腊语、中文和印地语的多语言金融考试问答基准。像CFA、EFPA和CPA等金融认证考试需要结构化领域推理，而标准NLP基准无法捕捉，跨语言时挑战更大。我们基于LangGraph构建了一个检索增强管道，用BGE-M3嵌入和FAISS索引检测查询语言并从30209条目的多语言知识库中检索语义相关示例。然后通过检索增强直接评分（RADS）对答案评分，读取候选选项字母的下一个token对数概率而非生成自由形式输出。对于低资源语言，使用加权倒数排名融合来融合每种语言和跨语言检索索引。模型选择是语言路由的，通过实验消融得出不同语言的路由模型。结果表明有效的多语言金融推理需要语言感知检索、模型路由和精心的评分策略选择。
英文摘要
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.
发表机构
- Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。
