SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wastl, Michelle, Vamvas, Jannis, Sennrich, Rico
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911624724480000
author Wastl, Michelle
Vamvas, Jannis
Sennrich, Rico
author_facet Wastl, Michelle
Vamvas, Jannis
Sennrich, Rico
contents Recognizing semantic differences across documents is crucial for text generation evaluation and content alignment, especially in cross-lingual settings. However, as a standalone task, it has received little attention. We address this by introducing SwissGov-RSD, the first naturalistic, document-level, cross-lingual dataset for semantic difference recognition. It encompasses a total of 224 multi-parallel documents in English--German, English--French, and English--Italian with token-level difference annotations by human annotators. We evaluate a variety of open-source and closed-source large language models as well as encoder models across different fine-tuning settings on this new benchmark. Our results show that current automatic approaches perform poorly compared to their performance on monolingual, sentence-level, and synthetic benchmarks, revealing a considerable gap for both LLMs and encoder models. We make our code and dataset publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07538
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents
Wastl, Michelle
Vamvas, Jannis
Sennrich, Rico
Computation and Language
Recognizing semantic differences across documents is crucial for text generation evaluation and content alignment, especially in cross-lingual settings. However, as a standalone task, it has received little attention. We address this by introducing SwissGov-RSD, the first naturalistic, document-level, cross-lingual dataset for semantic difference recognition. It encompasses a total of 224 multi-parallel documents in English--German, English--French, and English--Italian with token-level difference annotations by human annotators. We evaluate a variety of open-source and closed-source large language models as well as encoder models across different fine-tuning settings on this new benchmark. Our results show that current automatic approaches perform poorly compared to their performance on monolingual, sentence-level, and synthetic benchmarks, revealing a considerable gap for both LLMs and encoder models. We make our code and dataset publicly available.
title SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents
topic Computation and Language
url https://arxiv.org/abs/2512.07538