Research Papers 论文研究 5h ago Updated 1h ago 更新于 1小时前 44

XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answering XHotpotQA:多跳问答中的跨语言知识组合基准

XHotpotQA is a new benchmark for cross-lingual knowledge composition in multi-hop question answering, addressing a gap where existing multilingual benchmarks translate entire examples into one language, thereby hiding failures at language boundaries The benchmark models each instance as an evidence-dependency graph with explicit language assignments for questions, bridge evidence, answer-bearing evidence, and distractors The dataset contains 15,661 training and 7,405 validation instances with se 提出XHotpotQA基准测试,专门评估多跳问答中跨语言知识组合能力,解决现有基准翻译整个示例隐藏语言边界失败的问题 数据集包含15,661个训练实例和7,405个验证实例,每个实例建模为证据依赖图,问题、桥接证据、答案证据和干扰项均有明确语言分配 验证集中99.81%实例跨越问题到黄金证据的语言界面,95.60%使用不同语言的黄金段落 完全问题-证据语言不匹配导致Unicode感知答案F1降低10.25-15.79分,不同脚本证据导致11.98-23.70分差距 阅读器比适配选择器表现出更大的条件相关缺陷(10+分 vs 1.7-1.8分),为跨语言知识集成系统提供角色感知诊断工具

58
Hot 热度
72
Quality 质量
62
Impact 影响力

Analysis 深度分析

TL;DR

  • XHotpotQA is a new benchmark for cross-lingual knowledge composition in multi-hop question answering, addressing a gap where existing multilingual benchmarks translate entire examples into one language, thereby hiding failures at language boundaries
  • The benchmark models each instance as an evidence-dependency graph with explicit language assignments for questions, bridge evidence, answer-bearing evidence, and distractors
  • The dataset contains 15,661 training and 7,405 validation instances with sentence-level support supervision and supplied distractors
  • Full question-evidence language mismatch causes 10.25–15.79 lower Unicode-aware answer F1, while different-script evidence causes deficits of 11.98–23.70 points
  • The benchmark provides role-aware diagnostics and modular evaluation for systems that must integrate evidence across languages

Why It Matters

This benchmark directly addresses a critical blind spot in multilingual NLP evaluation: the failure modes that occur specifically at language boundaries within reasoning chains. For AI practitioners building multilingual QA systems, XHotpotQA offers a controlled testbed to diagnose and improve cross-lingual knowledge composition rather than relying on benchmarks that mask these failures through full translation.

Technical Details

  • Each instance is modeled as an evidence-dependency graph with explicit language assignments for the question, bridge evidence, answer-bearing evidence, and distractors, enabling fine-grained analysis of cross-lingual failure points
  • The dataset contains 15,661 training and 7,405 validation instances with sentence-level support supervision and supplied distractors, providing a controlled environment for evaluation
  • Validation statistics show 99.81% of items cross the question-to-gold-evidence language interface and 95.60% use gold paragraphs in different languages, ensuring substantial cross-lingual coverage
  • Empirical results across three reader artifacts demonstrate that full question-evidence mismatch reduces Unicode-aware answer F1 by 10.25–15.79 points compared to partial alignment, and different-script evidence causes deficits of 11.98–23.70 points
  • The adapted-selector component shows substantially smaller condition-associated deficits (1.71 and 1.78 points) compared to readers, highlighting the relative robustness of evidence selection versus composition under cross-lingual conditions

Industry Insight

  • Multilingual QA systems should invest in cross-lingual evidence selection and composition modules rather than relying on translation-based approaches, as language boundary failures represent a significant and under-evaluated source of error
  • The modular evaluation framework of XHotpotQA can guide targeted improvements in knowledge-intensive NLP pipelines, particularly for systems operating in low-resource or mixed-script environments
  • Benchmark designers and practitioners should consider role-aware diagnostics when evaluating multilingual systems, as aggregate metrics may obscure critical failure modes at specific points in the reasoning chain

TL;DR

  • 提出XHotpotQA基准测试,专门评估多跳问答中跨语言知识组合能力,解决现有基准翻译整个示例隐藏语言边界失败的问题
  • 数据集包含15,661个训练实例和7,405个验证实例,每个实例建模为证据依赖图,问题、桥接证据、答案证据和干扰项均有明确语言分配
  • 验证集中99.81%实例跨越问题到黄金证据的语言界面,95.60%使用不同语言的黄金段落
  • 完全问题-证据语言不匹配导致Unicode感知答案F1降低10.25-15.79分,不同脚本证据导致11.98-23.70分差距
  • 阅读器比适配选择器表现出更大的条件相关缺陷(10+分 vs 1.7-1.8分),为跨语言知识集成系统提供角色感知诊断工具

为什么值得看

这篇论文揭示了多语言问答系统中一个长期被忽视的关键问题:语言边界处的推理失败。对于构建真正多语言AI系统的研究者和工程师来说,XHotpotQA提供了第一个专门针对跨语言知识组合的受控评估基准,有助于诊断和改进系统在混合语言证据下的表现。

技术解析

  • XHotpotQA将每个问答实例建模为证据依赖图,明确分配问题、桥接证据、答案证据和干扰项的语言属性,提供句子级支持监督和预定义干扰项
  • 数据集规模:15,661个训练实例,7,405个验证实例,验证集99.81%跨越问题到黄金证据的语言界面,95.60%使用不同语言的黄金段落
  • 关键实验发现:完全问题-证据语言不匹配导致Unicode感知答案F1降低10.25-15.79分,不同脚本证据导致11.98-23.70分差距
  • 对比分析显示:适配选择器的条件相关缺陷仅1.71-1.78分,远小于阅读器的缺陷,表明选择器比阅读器更能容忍跨语言条件变化
  • 提供角色感知诊断、模块化评估和可审计的测试床,专门针对必须跨语言集成证据的知识系统

行业启示

  • 多语言AI系统评估需要专门设计跨语言推理基准,而非简单翻译单一语言数据集,否则无法发现语言边界处的系统性失败
  • 证据选择模块比答案生成模块对跨语言条件更鲁棒,系统设计应优先考虑增强选择器的跨语言泛化能力
  • 不同脚本(如拉丁字母vs西里尔字母)的跨语言组合带来更大挑战,需要特别关注字符级和脚本级对齐问题

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Benchmark 基准测试 Dataset 数据集 Evaluation 评测 Research 科学研究 LLM 大模型