Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Enze, Wang, Jiaying, Xiao, Mengxi, Liu, Jifei, Kuang, Ziyan, Dong, Rui, Dong, Eric, Ananiadou, Sophia, Peng, Min, Xie, Qianqian
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.09116
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909839526985728
author Zhang, Enze
Wang, Jiaying
Xiao, Mengxi
Liu, Jifei
Kuang, Ziyan
Dong, Rui
Dong, Eric
Ananiadou, Sophia
Peng, Min
Xie, Qianqian
author_facet Zhang, Enze
Wang, Jiaying
Xiao, Mengxi
Liu, Jifei
Kuang, Ziyan
Dong, Rui
Dong, Eric
Ananiadou, Sophia
Peng, Min
Xie, Qianqian
contents Large language models (LLMs) have substantially advanced machine translation (MT), yet their effectiveness in translating web novels remains unclear. Existing benchmarks rely on surface-level metrics that fail to capture the distinctive traits of this genre. To address these gaps, we introduce DITING, the first comprehensive evaluation framework for web novel translation, assessing narrative and cultural fidelity across six dimensions: idiom translation, lexical ambiguity, terminology localization, tense consistency, zero-pronoun resolution, and cultural safety, supported by over 18K expert-annotated Chinese-English sentence pairs. We further propose AgentEval, a reasoning-driven multi-agent evaluation framework that simulates expert deliberation to assess translation quality beyond lexical overlap, achieving the highest correlation with human judgments among seven tested automatic metrics. To enable metric comparison, we develop MetricAlign, a meta-evaluation dataset of 300 sentence pairs annotated with error labels and scalar quality scores. Comprehensive evaluation of fourteen open, closed, and commercial models reveals that Chinese-trained LLMs surpass larger foreign counterparts, and that DeepSeek-V3 delivers the most faithful and stylistically coherent translations. Our work establishes a new paradigm for exploring LLM-based web novel translation and provides public resources to advance future research.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09116
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation
Zhang, Enze
Wang, Jiaying
Xiao, Mengxi
Liu, Jifei
Kuang, Ziyan
Dong, Rui
Dong, Eric
Ananiadou, Sophia
Peng, Min
Xie, Qianqian
Computation and Language
Large language models (LLMs) have substantially advanced machine translation (MT), yet their effectiveness in translating web novels remains unclear. Existing benchmarks rely on surface-level metrics that fail to capture the distinctive traits of this genre. To address these gaps, we introduce DITING, the first comprehensive evaluation framework for web novel translation, assessing narrative and cultural fidelity across six dimensions: idiom translation, lexical ambiguity, terminology localization, tense consistency, zero-pronoun resolution, and cultural safety, supported by over 18K expert-annotated Chinese-English sentence pairs. We further propose AgentEval, a reasoning-driven multi-agent evaluation framework that simulates expert deliberation to assess translation quality beyond lexical overlap, achieving the highest correlation with human judgments among seven tested automatic metrics. To enable metric comparison, we develop MetricAlign, a meta-evaluation dataset of 300 sentence pairs annotated with error labels and scalar quality scores. Comprehensive evaluation of fourteen open, closed, and commercial models reveals that Chinese-trained LLMs surpass larger foreign counterparts, and that DeepSeek-V3 delivers the most faithful and stylistically coherent translations. Our work establishes a new paradigm for exploring LLM-based web novel translation and provides public resources to advance future research.
title DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation
topic Computation and Language
url https://arxiv.org/abs/2510.09116