EnSiTa is a trilingual multi‑domain parallel dataset and benchmark for English, Sinhala, and Tamil. It contains human post‑edited training data across seven domains and professionally translated test sets for those domains plus an additional one, all produced through a multi‑year, rigorously quality‑controlled process. The authors use EnSiTa to conduct a comprehensive study of domain‑specific machine translation across six language directions, comparing from‑scratch Transformers, pre‑trained models, and decoder‑only LLMs under various training‑data sizes, model scales, and domain settings.
By Surangika Ranathunga, Nisansa de Silva, Aloka Fernando, Kavindu Warnakulasuriya, Isuru Wijesiri, Menan Velayuthan, Charitha Rathnayaka, Thivaharan Varatharajan, Sajeevi Silva, Piumi Kandanaarachchi, Uthayasanker Thayasivam
arXiv:2608.12018v2 Announce Type: replace
Abstract: Neural Machine Translation (NMT) and Large Language Models (LLMs) excel at cross-lingual tasks but often fail to capture intra-lingual morphologica...
By Rakib Ullah, Md. Ruhul Islam, Tanbir Ahmed, Nayan Kumar Nath
arXiv:2606. 08272v1 Announce Type: cross Abstract: AgriGov is a curated, trilingual (English-Hindi-Marathi) dataset designed to address the scarcity of domain-grounded multilingual resources for agricultural policies and farmer welfare schemes.
By Mohsina Bilal, Gopakumar G
arXiv:2606. 25365v2 Announce Type: replace-cross Abstract: We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair.
By Chormi Zimik Vashai, Agniva Maiti
VakyArth is the first pragmatic benchmark for Indic languages, covering Hindi, Punjabi, Tamil, and Malayalam. It tests models on five pragmatic phenomena—deixis, speech acts, implicature, social pragmatics, and coherence—using multiple-choice questions, natural language inference, and translation tasks authored by native speakers. Evaluation of multilingual LLMs shows consistent failures on pragmatic meanings rooted in Indic linguistic and cultural conventions, with systematic differences across languages and tasks.
By Usneek Singh, Poorvaja Veera Balaji Kumar, Parth Nanda, Anand Madhusoodanan, Geyang Guo, Wei Xu, Junyi Jessy L
The paper investigates how to fairly compare language models across languages, noting that current evaluation methods vary widely and lack empirical validation. By training controlled monolingual models on parallel data and testing multilingual LLMs, the authors find that many normalized metrics suffer from biases due to tokenization, encoding, and orthographic differences. Instead, they recommend using sentence‑level negative log‑likelihood over semantically equivalent sequences for more reliable cross‑lingual comparisons.
By Xiulin Yang, Ethan Gotlieb Wilcox, Catherine Arnett