Cover Image

Lost in Literalism: How Supervised Training Shapes Translationese in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yafu, Zhang, Ronghao, Wang, Zhilin, Zhang, Huajian, Cui, Leyang, Yin, Yongjing, Xiao, Tong, Zhang, Yue
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What Have We Achieved on Non-autoregressive Translation?
by: Li, Yafu, et al.
Published: (2024)

Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text
by: Li, Yafu, et al.
Published: (2024)

LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translation
by: Yin, Yongjing, et al.
Published: (2024)

MAGE: Machine-generated Text Detection in the Wild
by: Li, Yafu, et al.
Published: (2023)

Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese
by: Liu, Yikang, et al.
Published: (2025)

Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation
by: Wein, Shira, et al.
Published: (2023)

Training Models on Dialects of Translationese Shows How Lexical Diversity and Source-Target Syntactic Similarity Shape Learning
by: Kunz, Jenny
Published: (2026)

Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing
by: Wang, Zhilin, et al.
Published: (2025)

Semformer: Transformer Language Models with Semantic Planning
by: Yin, Yongjing, et al.
Published: (2024)

Characterizing, Evaluating, and Optimizing Complex Reasoning
by: Zhang, Haoran, et al.
Published: (2026)

Decoding Machine Translationese in English-Chinese News: LLMs vs. NMTs
by: Kong, Delu, et al.
Published: (2025)

SEE: Continual Fine-tuning with Sequential Ensemble of Experts
by: Wang, Zhilin, et al.
Published: (2025)

Pretraining Language Models Using Translationese
by: Doshi, Meet, et al.
Published: (2024)

Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation
by: Zhang, Haoran, et al.
Published: (2025)

From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning
by: Li, Yafu, et al.
Published: (2025)

Alleviating Hallucinations of Large Language Models through Induced Hallucinations
by: Zhang, Yue, et al.
Published: (2023)

Potential and Challenges of Model Editing for Social Debiasing
by: Yan, Jianhao, et al.
Published: (2024)

Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
by: Zhang, Hongbin, et al.
Published: (2026)

Keys to Robust Edits: from Theoretical Insights to Practical Advances
by: Yan, Jianhao, et al.
Published: (2024)

New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR
by: Wang, Zhilin, et al.
Published: (2026)

Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationese
by: Borah, Angana, et al.
Published: (2023)

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers
by: Li, Qintong, et al.
Published: (2024)

A Dataset for Probing Translationese Preferences in English-to-Swedish Translation
by: Kunz, Jenny, et al.
Published: (2026)

Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
by: Huang, Shulin, et al.
Published: (2025)

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
by: Li, Zherui, et al.
Published: (2025)

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
by: Su, Yi, et al.
Published: (2025)

The Comparison of Translationese in Machine Translation and Human Transation in terms of Translation Relations
by: Zhou, Fan
Published: (2024)

Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation
by: Tian, Yanzhi, et al.
Published: (2026)

Mitigating Translationese in Low-resource Languages: The Storyboard Approach
by: Kuwanto, Garry, et al.
Published: (2024)

Leveraging Entailment Judgements in Cross-Lingual Summarisation
by: Zhang, Huajian, et al.
Published: (2024)

Under the Shadow of Babel: How Language Shapes Reasoning in LLMs
by: Wang, Chenxi, et al.
Published: (2025)

KOSMOS-2.5: A Multimodal Literate Model
by: Lv, Tengchao, et al.
Published: (2023)

Understanding In-Context Learning from Repetitions
by: Yan, Jianhao, et al.
Published: (2023)

An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
by: Luo, Yun, et al.
Published: (2023)

Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Literal Extraction, Logical Inference, and Hallucination Risks in Long-Context LLMs
by: Ebrahimzadeh, Amirali, et al.
Published: (2026)

Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning
by: Guo, Jiaxing, et al.
Published: (2025)

Retracing the Past: LLMs Emit Training Data When They Get Lost
by: Ko, Myeongseob, et al.
Published: (2025)

CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation
by: Chen, Tong, et al.
Published: (2024)

Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks
by: Li, Qintong, et al.
Published: (2023)

TIM: Teaching Large Language Models to Translate with Comparison
by: Zeng, Jiali, et al.
Published: (2023)