待翻译：Evaluating Dedicated Monolingual and Joint Multilingual Causal Models for Dravidian Languages

AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。

--> [Submitted on 7 Aug 2026] Title:Evaluating Dedicated Monolingual and Joint Multilingual Causal Models for Dravidian Languages View a PDF of the paper titled Evaluating Dedicated Monolingual and Joint Multilingual Causal Models for Dravidian Languages, by Venkata Naga Sai Vishnu Rohit Pulipaka View PDF HTML (experimental) Abstract:Dravidian languages, mainly Tamil, Telugu, Kannada, and Malayalam make up only a small part of the data used to train multilingual language models, so it's not clear how much per-language ability these models actually keep. I have trained five GPT-2 architecture models from scratch to compare four monolingual models (one each for Tamil, Telugu, Kannada, and Malayalam, each with its own 32K-vocabulary subword tokenizer) against one multilingual model sharing a 64K-vocabulary subword tokenizer across all four languages. All the 5 models are trained on cleaned CC-100, Wikipedia, and Samanantar data. I have tested the models on perplexity, bits-per-byte, tokenizer efficiency, and fine-tuning results which are compared against mGPT. The monolingual models outperform mGPT on sentiment classification and named entity recognition, and their tokenizers proved more efficient than the shared multilingual model across all the languages tested. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2608.07727 [cs.CL] (or arXiv:2608.07727v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.07727 arXiv-issued DOI via DataCite (pending registration) Submission history From: Venkata Naga Sai Vishnu Rohit Pulipaka [view email] [v1] Fri, 7 Aug 2026 19:33:11 UTC (31 KB) Full-text links: Access Paper: View a PDF of the paper titled Evaluating Dedicated Monolingual and Joint Multilingual Causal Models for Dravidian Languages, by Venkata Naga Sai Vishnu Rohit Pulipaka View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: 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?)