Cross-lingual Biography Enrichment via Claim Extraction and Alignment
cs.CL, cs.AI
Submitted: 2026-08-24
Updated: 2026-08-26
Comments: Accepted by EMNLP 2026 main conference
Code: https://github.com/MeloS7/cross_lingual_biography_enrichment
License: http://creativecommons.org/licenses/by/4.0/
The gist: English Wikipedia is often treated as the default encyclopedic source, yet non-English Wikipedia editions can contain richer locally grounded information for long-tail figures.
Terminology
Abstract
English Wikipedia is often treated as the default encyclopedic source, yet non-English Wikipedia editions can contain richer locally grounded information for long-tail figures. We study cross-lingual biography enrichment: enriching an existing English biography with facts supported by a non-English biography about the same person. Focusing on women from non-English-speaking contexts, we introduce CLAW-4L, a benchmark consisting of 300 Wikipedia biography pairs linking an English biography with its French, Chinese or Azerbaijani counterpart, along with claim annotations and a fine-grained claim-pair relation corpus. We propose a claim-based enrichment framework that extracts English claims from both biographies, aligns them to identify enrichment evidence from the non-English biography, and rewrites the English biography using the selected claims. Our results show that non-English Wikipedia biographies provide valuable evidence for improving English biography coverage, while lower-resource settings remain challenging.
Sources
- REALM: Retrieval-Augmented Language Model Pre-Training
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- OpenAI GPT-5 System Card
- FEVER: a large-scale dataset for Fact Extraction and VERification
- Qwen3 Technical Report
- SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering