# Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs arXiv: https://arxiv.org/abs/2403.05434 ยท HTML: https://mlsanity.com/paper/2403.05434/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Builds on 24 of its 28 references that are in the map. - First posted on arXiv 8 Mar 2024. ## Builds on (most cited first, 24 of 24) - [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022) - [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019) - [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022) - [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019) - [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023) - [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023) - [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020) - [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022) - [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020) - [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023) - [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021) - [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023) - [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020) - [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023) - [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023) - [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023) - [XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation](https://mlsanity.com/paper/2104.07412/) (2021) - [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023) - [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023) - [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021) - [IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding](https://mlsanity.com/paper/2009.05387/) (2020) - [Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages](https://mlsanity.com/paper/2212.05409/) (2022) - [AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain](https://mlsanity.com/paper/2110.13434/) (2021) - [Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset](https://mlsanity.com/paper/2311.05113/) (2023) ## Built on by (most cited first, 7 of 7) - [Efficient Continual Pre-training of LLMs for Low-resource Languages](https://mlsanity.com/paper/2412.10244/) (2024) - [Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges](https://mlsanity.com/paper/2509.11570/) (2025) - [Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities](https://mlsanity.com/paper/2510.07037/) (2025) - [Evaluation of LLMs in Medical Text Summarization: The Role of Vocabulary Adaptation in High OOV Settings](https://mlsanity.com/paper/2505.21242/) (2025) - [Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detection](https://mlsanity.com/paper/2412.12761/) (2024) - [Software Performance Engineering for Foundation Model-Powered Software](https://mlsanity.com/paper/2411.09580/) (2024) - [CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression](https://mlsanity.com/paper/2606.24083/) (2026) ## Abstract (arXiv) Large Language Models (LLMs) exhibit impressive zero/few-shot inference and generation quality for high-resource languages (HRLs). A few of them have been trained on low-resource languages (LRLs) and give decent performance. Owing to the prohibitive costs of training LLMs, they are usually used as a network service, with the client charged by the count of input and output tokens. The number of tokens strongly depends on the script and language, as well as the LLM's subword vocabulary. We show that LRLs are at a pricing disadvantage, because the well-known LLMs produce more tokens for LRLs than HRLs. This is because most currently popular LLMs are optimized for HRL vocabularies. Our objective is to level the playing field: reduce the cost of processing LRLs in contemporary LLMs while ensuring that predictive and generative qualities are not compromised. As means to reduce the number of tokens processed by the LLM, we consider code-mixing, translation, and transliteration of LRLs to HRLs. We perform an extensive study using the IndicXTREME classification and six generative tasks dataset, covering 15 Indic and 3 other languages, while using GPT-4 (one of the costliest LLM services released so far) as a commercial LLM. We observe and analyze interesting patterns involving token count, cost, and quality across a multitude of languages and tasks. We show that choosing the best policy to interact with the LLM can reduce cost by 90% while giving better or comparable performance compared to communicating with the LLM in the original LRL.