大模型
arxiv.org ·
TransClean：检测并提取大语言模型输出中干净译文的基准
该论文指出 LLM 用于机器翻译时输出常夹带语言标签、解释或双语重复等“翻译噪声”，但缺乏专门基准与系统研究。作者分析 12 个 LLM 在 22 个语向上的逾 79 万条翻译输出，归纳出 12 种反复出现的噪声模式，分为格式噪声与内容噪声两类，并据此构建 TransClean 基准，包含 9,900 对噪声与干净译文（8,800 条合成、1,100 条人工整理）。论文在基准上评估两类抽取方案：利用翻译质量估计模型做 span 检测的抽取方法，以及提示 LLM 隔离译文的抽取方法，称这是首个系统评估并改进 LLM 翻译输出干净度的框架。
AI推荐理由 arXiv 正式提交的 cs.CL 论文，作者为 Shenbin Qian 与 Yves Scherrer，摘要给出明确规模：分析 12 个 LLM、22 个语向、逾 79 万条翻译输出，归纳出 12 类翻译噪声（格式噪声与内容噪声），并构建 TransClean 基准，含 9,900 对噪声/干净译文（8,800 条合成 + 1,100 条人工整理），对比基于 span 的抽取方法与 LLM 提示抽取方法。新信息具体、可复现，对 LLM 机器翻译输出后处理与评测有直接用途；局限是仅覆盖翻译任务，且摘要未给出两种抽取方法的具体效果数值，实际增益需看正文。
72
正文
Computer Science > Computation and Language
arXiv:2609.11399 (cs)
[Submitted on 10 Sep 2026]
Title:TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs
Authors:Shenbin Qian, Yves Scherrer
View a PDF of the paper titled TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs, by Shenbin Qian and Yves Scherrer
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) are increasingly used for machine translation, yet their outputs often contain additional text beyond the translation itself, such as language labels, explanations or bilingual repetitions, which we term translation noise. Despite its prevalence, this problem lacks dedicated benchmarks and systematic study. We analyze over 790,000 translation outputs from 12 LLMs across 22 language pairs (LPs) and identify 12 recurring noise patterns, which we group into formatting and content noise. Building on the observed patterns, we construct TransClean, a controlled benchmark of 9,900 pairs of noisy and clean translation outputs, comprising 8,800 synthetically generated instances and 1,100 manually curated authentic instances. We evaluate two extraction approaches on the TransClean benchmark: 1) a span-based extraction method leveraging translation quality estimation models for span detection, and 2) an LLM-based extraction method that prompts an LLM to isolate the translation. Our benchmark and analysis provide the first systematic framework to evaluate and improve the cleanliness of LLM translation outputs.
Comments:
Subjects:
Computation and Language (cs.CL)
Cite as:
arXiv:2609.11399 [cs.CL]
(or
arXiv:2609.11399v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.11399
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Shenbin Qian [view email]
[v1]
Thu, 10 Sep 2026 11:32:18 UTC (12,084 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs, by Shenbin Qian and Yves Scherrer
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)