Problem
Research questions and friction points this paper is trying to address.
Cross-lingual Knowledge Composition
Multi-hop Question Answering
Mixed-language Evidence
XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question Answering
🤖 AI Summary
为解决多语言证据整合问题，本文引入XHotpotQA基准，通过构建跨语言证据依赖图来评估和改进多跳问答系统中的知识组合能力。
📝 Abstract
Knowledge-intensive multi-hop question answering requires systems to select evidence and compose dependent facts, yet multilingual benchmarks usually translate an entire example into one language. This hides failures at language boundaries inside the reasoning chain. We introduce XHotpotQA, a controlled benchmark for cross-lingual knowledge composition over mixed-language evidence. Each instance is modeled as an evidence-dependency graph whose question, bridge evidence, answer-bearing evidence, and distractors have explicit language assignments. The audited resource contains 15,661 training and 7,405 validation instances, with sentence-level support supervision and supplied distractors. In validation, 99.81% of items cross the question-to-gold-evidence language interface and 95.60% use gold paragraphs in different languages. Across three reader artifacts, full question-evidence mismatch is associated with 10.25 to 15.79 lower Unicode-aware answer F1 than partial alignment, and different-script evidence with deficits of 11.98 to 23.70 points; the corresponding adapted-selector contrasts are 1.71 and 1.78 points. Under this supplied-candidate design, the evaluated readers therefore show substantially larger condition-associated deficits than the selector. XHotpotQA provides role-aware diagnostics, modular evaluation, and an audited test bed for knowledge-based systems that must integrate evidence across languages.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Cross-lingual Knowledge Composition
Multi-hop Question Answering
Evidence-dependency Graph
Language Boundaries
Role-aware Diagnostics
🔎 Similar Papers
No similar papers found.
