ACL Findings2026
ETHICA-MT: Introducing a Framework and Dataset for Studying Ethical Orientations in LLM-based Machine Translation
Abstract
Translation is a fundamentally value-laden process that requires the translator to make decisions and judgments that have ethical implications. However, even though large language models (LLMs) are increasingly used for translation tasks, LLMs have not been systematically examined for their default ethical tendencies or their abilities to employ and prioritize specified ethical approaches in conflicted translation situations. To address this gap, we present ETHICA-MT, a framework for examining ethical reasoning and implementation in LLM-based machine translation. Drawing on diverse ethical approaches from the translation studies literature, we formalize a conceptual framework and construct a multilingual benchmark, ETHICA-MT BENCH, that covers six languages and highlights ethical conflicts arising from competing ethical approaches in a variety of translation scenarios. Our empirical study shows that current models predominantly default to an ethical stance favoring 'faithful representation' to the source text, and vary in their ability to implement specified ethics at the expense of others. Finally, we highlight the basic challenges of automatically and manually evaluating the models' ethical stances. Note. This paper contains examples that the reader might find offensive. Reader's discretion is advised. These examples do not reflect our views.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on6
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- COMET: A Neural Framework for MT EvaluationRicardo Rei, Craig Stewart, Ana C. Farinha, Alon LavieEMNLP 2020 · 6 citations
- Aya Model: An Instruction Finetuned Open-Access Multilingual Language ModelAhmet Üstün, Viraat Aryabumi, Zheng Xin Yong, Wei-Yin Ko et al.ACL 2024
- CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WebHolger Schwenk, Guillaume Wenzek, Sergey Edunov, Edouard Grave et al.ACL 2021
Related papers
- Do Morals Guide How LLMs Think? The Role of Ethical Perspectives in General Problem SolvingIseo Kim, Eunjin Hong, Juae KimACL 2026
- PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health EthicsYaling Shen, Stephanie Fong, Yiwen Jiang, Zimu Wang et al.ACL Findings 2026 · 1 citation
- The Heterogeneous Safety Impacts of Benign Multilingual Fine-TuningWill Hawkins, Kai Rawal, Jonathan Rystrøm, Stratis Tsirtsis et al.ICML 2026
- Advancing Automated Ethical Profiling in SE: a Zero-Shot Evaluation of LLM ReasoningPatrizio Migliarini, Mashal Afzal Memon, Marco Autili, Paola InverardiASE 2025
- Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language ModelsZiyi Zhou, Xinwei Guo, Jiashi Gao, Xiangyu Zhao et al.NeurIPS 2024
