# Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?

arXiv: https://arxiv.org/abs/2403.01929 · HTML: https://mlsanity.com/paper/2403.01929/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 85 references that are in the map.
- First posted on arXiv 4 Mar 2024.

## Builds on (most cited first, 30 of 62)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning](https://mlsanity.com/paper/2005.00333/) (2020)
- [The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants](https://mlsanity.com/paper/2308.16884/) (2023)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)

## Built on by (most cited first, 11 of 11)

- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages](https://mlsanity.com/paper/2406.12739/) (2024)
- [A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs](https://mlsanity.com/paper/2406.17377/) (2024)
- [It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs](https://mlsanity.com/paper/2508.19089/) (2025)
- [ABC Align: Large Language Model Alignment for Safety & Accuracy](https://mlsanity.com/paper/2408.00307/) (2024)
- [Language Fusion for Parameter-Efficient Cross-lingual Transfer](https://mlsanity.com/paper/2501.06892/) (2025)
- [Blessing of Multilinguality: A Systematic Analysis of Multilingual In-Context Learning](https://mlsanity.com/paper/2502.11364/) (2025)
- [Grow Up and Merge: Scaling Strategies for Efficient Language Adaptation](https://mlsanity.com/paper/2512.10772/) (2025)
- [Train More Parameters But Mind Their Placement: Insights into Language Adaptation with PEFT](https://mlsanity.com/paper/2412.12674/) (2024)
- [Spoken Language Understanding on Unseen Tasks With In-Context Learning](https://mlsanity.com/paper/2505.07731/) (2025)
- [Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages](https://mlsanity.com/paper/2506.19187/) (2025)

## Abstract (arXiv)

Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has gained popularity recently with the advent of LLMs due to its simplicity and sample efficiency. Prior research has conducted only limited investigation into how these approaches work for multilingual few-shot learning, and the focus so far has been mostly on their performance. In this work, we present an extensive and systematic comparison of the three approaches, testing them on 6 high- and low-resource languages, three different NLU tasks, and a myriad of language and domain setups. Importantly, performance is only one aspect of the comparison, where we also analyse the approaches through the optics of their computational, inference and financial costs. Our observations show that supervised instruction tuning has the best trade-off between performance and resource requirements. As another contribution, we analyse the impact of target language adaptation of pretrained LLMs and find that the standard adaptation approaches can (superficially) improve target language generation capabilities, but language understanding elicited through ICL does not improve and remains limited, with low scores especially for low-resource languages.