From Script to Semantics: Prompting Strategies for African NLI

• URL: http://arxiv.org/abs/2606.03304v1
• Date: Tue, 02 Jun 2026 08:20:10 GMT
• Title: From Script to Semantics: Prompting Strategies for African NLI
• Abstract summary: We present a systematic study of prompting strategies for Natural Language Inference (NLI) in Swahili, Yoruba, and Hausa.<n>We evaluate five prompting strategies Baseline (zero-shot), Script-Aware, Language Specific, Contrastive, and Native-Label Self-Translation (NL-STP)<n>We find a significant difference in performance of class wise across strategies with highly neutral class collapse and high prediction skew in some configurations.
• Score: 1.0705399532413615
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains underexplored especially under pure prompting without fine-tuning. We present a systematic study of prompting strategies for Natural Language Inference (NLI) in Swahili, Yoruba, and Hausa using the AfriXNLI benchmark. We evaluate five prompting strategies Baseline (zero-shot), Script-Aware, Language Specific, Contrastive, and Native-Label Self-Translation (NL-STP) across two mid-sized open weight models (Llama3.2-3B and Gemma3-4B). To isolate the effect of prompt design, the effect of few-shot examples and Chain-of-Thought reasoning is eliminated in our study. We find a significant difference in performance of class wise across strategies with highly neutral class collapse and high prediction skew in some configurations. Contrastive prompting proves to be the most reliable and steadily improving strategy over language and model and has better balance of class behavior and balance of overall accuracy gains. Notably, well-constructed prompts are sufficient to beat more powerful baselines that are provided with few-shot prompts and Chain-of-Thought prompts. We have found that prompt formulation is essential to multilingual NLI with low-resource languages and that language aware decision structuring can be used to meaningfully enhance robustness in resource challenged settings.

Related papers

• Are you speaking my languages? On spoken language adherence in multimodal LLMs [1.554397085362411]
  Large Language Model (LLM) based Automatic Speech Recognition (ASR) enables seamless multilingual use.<n>Models often misidentify the output language, compromising transcription fidelity and downstream application quality.<n>We propose a soft prompting approach that hints at potential spoken languages without strictly constraining the output.
  arXiv  Detail & Related papers  (2026-06-15T20:44:42Z)
• No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs [22.409170147732464]
  We evaluate prompting strategies across ten languages of different resource levels and four benchmarks.<n>We introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance.
  arXiv  Detail & Related papers  (2026-04-18T09:40:51Z)
• What Language is This? Ask Your Tokenizer [32.28976119949841]
  Language Identification (LID) is an important component of many multilingual natural language processing pipelines.<n>We introduce UniLID, a simple and efficient LID method based on the UnigramLM tokenization algorithm.<n>Our formulation is data- and compute-efficient, supports incremental addition of new languages without retraining existing models.
  arXiv  Detail & Related papers  (2026-02-19T18:58:39Z)
• Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages [61.18573330164572]
  System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time.<n>This paper presents a comprehensive study of how different system prompts steer models toward accurate and robust cross-lingual behavior.
  arXiv  Detail & Related papers  (2025-12-02T14:54:54Z)
• CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention [9.76878200328024]
  Large Language Models (LLMs) often exhibit knowledge disparities across languages.<n>We introduce textitCausalAbstain, a method that helps LLMs determine whether to utilize multiple generated feedback responses.<n>Experiments demonstrate that textitCausalAbstain effectively selects helpful feedback and enhances abstention decisions with interpretability.
  arXiv  Detail & Related papers  (2025-05-31T11:35:31Z)
• PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks [57.86928556668849]
  Large Language Models (LLMs) have recently demonstrated impressive few-shot learning capabilities through in-context learning (ICL)<n>ICL performance is highly dependent on the choice of few-shot demonstrations, making the selection of the most optimal examples a persistent research challenge.<n>In this work, we propose PromptRefine, a novel Alternating Minimization approach for example selection that improves ICL performance on low-resource Indic languages.
  arXiv  Detail & Related papers  (2024-12-07T17:51:31Z)
• Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet? [82.02076369811402]
  Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. 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. Our observations show that supervised instruction tuning has the best trade-off between performance and resource requirements.
  arXiv  Detail & Related papers  (2024-03-04T10:48:13Z)
• Efficient Spoken Language Recognition via Multilabel Classification [53.662747523872305]
  We show that our models obtain competitive results while being orders of magnitude smaller and faster than current state-of-the-art methods. Our multilabel strategy is more robust to unseen non-target languages compared to multiclass classification.
  arXiv  Detail & Related papers  (2023-06-02T23:04:19Z)
• Multilingual Relation Classification via Efficient and Effective Prompting [9.119073318043952]
  We present the first work on prompt-based multilingual relation classification (RC) We introduce an efficient and effective method that constructs prompts from relation triples and involves only minimal translation for the class labels. We evaluate its performance in fully supervised, few-shot and zero-shot scenarios, and analyze its effectiveness across 14 languages.
  arXiv  Detail & Related papers  (2022-10-25T08:40:23Z)
• A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference [54.678516076366506]
  Natural Language Inference (NLI) is a growingly essential task in natural language understanding. Here we propose a multi-level supervised contrastive learning framework named MultiSCL for low-resource natural language inference.
  arXiv  Detail & Related papers  (2022-05-31T05:54:18Z)
• Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models [86.02610674750345]
  Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks. We apply 14 adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations. All the language models and robust training methods we tested perform poorly on AdvGLUE, with scores lagging far behind the benign accuracy.
  arXiv  Detail & Related papers  (2021-11-04T12:59:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.