Metaheuristic Optimization of Prompt Structures for Low-Resource Language Models

Authors

  • Abdulrahman Al-Harthy * Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia.
  • Nguyen Thi Lan School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, Vietnam.

https://doi.org/10.48313/maa.v3i3.116

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural Language Processing (NLP) tasks when guided by carefully designed prompts. However, their performance degrades substantially on low-resource languages, where limited pretraining data and the absence of large-scale labeled corpora render conventional prompt engineering strategies ineffective. In this paper, we introduce Evolutionary Prompt Optimization for Low-Resource Language Models (EvoPrompt-LR), a novel framework that employs a hybrid Genetic Algorithm with Simulated Annealing (GA-SA) to automatically discover optimal prompt structures for low-resource languages. EvoPrompt-LR features four key innovations: 1) a hierarchical prompt genome encoding that jointly optimizes instruction templates, in-context example selection and ordering, Chain-of-Thought (CoT) scaffold structures, and output format specifications, 2) a cross-lingual fitness transfer mechanism that evaluates prompt candidates on high-resource proxy languages before selectively fine-evaluating top candidates on the target low-resource language, reducing expensive evaluations by approximately 80%, 3) semantic diversity preservation via embedding-space crowding distance to maintain a diverse population of prompt candidates, and 4) language-specific mutation operators that respect the morphological and syntactic constraints of typologically diverse languages, including agglutinative (Vietnamese, Turkish, Uzbek), fusional (Arabic), and isolating (Khmer) language families. We evaluate EvoPrompt-LR on six low-resource languages Arabic (dialectal), Vietnamese, Swahili, Yoruba, Uzbek, and Khmer across four NLP tasks: Sentiment analysis, Named Entity Recognition (NER), Question Answering (QA), and text summarization, using LLaMA-3-8B, Mistral-7B, and AceGPT-7B as base models. Experimental results demonstrate that EvoPrompt-LR achieves improvements of 8–22% in accuracy and F1 score over the strongest baselines, with the largest gains observed on truly low-resource languages (Yoruba: +22%, Khmer: +19%). On four of six languages, EvoPrompt-LR attains performance competitive with Supervised Fine-Tuning (SFT) approaches that use 100× more labeled data.

Keywords:

Low-resource languages, Metaheuristic, Genetic algorithm, Large language models, Natural language processing

References

  1. [1] Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., … ., & Amodei, D. (2020). Language models are few-shot learners. Advances in neural information processing systems (Vol. 33, pp. 1877–1901). NeurIPS Foundation https://proceedings.neurips.cc/paper_files/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html
  2. [2] Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M. A., Lacroix, T., … ., & Lample, G. (2023). LLaMA: Open and efficient foundation language models. https://doi.org/10.48550/arXiv.2302.13971
  3. [3] Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., … ., & Scialom, T. (2023). Llama 2: Open foundation and fine-tuned chat models. https://doi.org/10.48550/arXiv.2307.09288
  4. [4] Meta AI. (2024). Introducing meta Llama 3: The most capable openly available LLM to date. https://ai.meta.com/blog/meta-llama-3/
  5. [5] Jiang, Y., Li, X., Zhu, G., Li, H., Deng, J., Han, K., … ., & Zhang, R. (2023). Mistral 7B. https://doi.org/10.48550/arXiv.2310.06825
  6. [6] Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM computing surveys, 55(9), 1–35. https://doi.org/10.1145/3560815
  7. [7] Zhao, Z., Wallace, E., Feng, S., Klein, D., & Singh, S. (2021). Calibrate before use: Improving few-shot performance of language models. Proceedings of the 38th international conference on machine learning (Vol. 139, pp. 12697–12706). PMLR. https://proceedings.mlr.press/v139/zhao21c.html
  8. [8] Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., … ., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems (Vol. 35, pp. 24824–24837). Curran Associates, Inc. https://doi.org/10.52202/068431-1800
  9. [9] Wang, X., Wei, J., Schuurmans, D., Le, Q. V., Chi, E. H., Narang, S., Chowdhery, A., & Zhou, D. (2023). Self-consistency improves chain of thought reasoning in language models. The eleventh international conference on learning representations (ICLR 2023). OpenReview. https://openreview.net/forum?id=1PL1NIMMrw
  10. [10] Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T., Cao, Y., & Narasimhan, K. (2023). Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems (Vol. 36, pp. 11809–11822). Curran Associates, Inc. https://doi.org/10.52202/075280-0517
  11. [11] Zhang, Z., Zhang, A., Li, M., & Smola, A. (2023). Automatic chain of thought prompting in large language models. The eleventh international conference on learning representations (ICLR 2023). OpenReview. https://openreview.net/forum?id=5NTt8GFjUHkr
  12. [12] Joshi, P., Santy, S., Budhiraja, A., Bali, K., & Choudhury, M. (2020). The state and fate of linguistic diversity and inclusion in the NLP world. Proceedings of the 58th annual meeting of the association for computational linguistics (pp. 6282–6293). Online: Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.560
  13. [13] Ahuja, K., Diddee, H., Hada, R., Ochieng, M., Ramesh, K., Jain, P., … ., & Sitaram, S. (2023). MEGA: Multilingual evaluation of generative AI. Proceedings of the 2023 conference on empirical methods in natural language processing (pp. 4232–4267). Singapore: Association for Computational Linguistics. https://doi.org/ 10.18653/v1/2023.emnlp-main.258
  14. [14] Lai, V. D., Ngo, N., Pouran Ben Veyseh, A., Man, H., Dernoncourt, F., Bui, T., & Nguyen, T. H. (2023). ChatGPT beyond English: Towards a comprehensive evaluation of large language models in multilingual learning. Findings of the association for computational linguistics: EMNLP 2023 (pp. 13171–13189). Singapore: Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-emnlp.878
  15. [15] Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., … ., & Stoyanov, V. (2020). Unsupervised cross-lingual representation learning at scale. Proceedings of the 58th annual meeting of the association for computational linguistics (pp. 8440–8451). Online: Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.747
  16. [16] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics: Human language technologies, Volume 1 (long and short papers) (pp. 4171–4186). Minneapolis, Minnesota: Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
  17. [17] Pfeiffer, J., Goyal, N., Lin, X. V., Li, X., Cross, J., Riedel, S., & Artetxe, M. (2022). Lifting the curse of multilinguality by pre-training modular transformers. Proceedings of the 2022 conference of the north american chapter of the association for computational linguistics: human language technologies (pp. 3479–3495). Seattle, United States: Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.naacl-main.255
  18. [18] Zhou, Y., Muresanu, A. I., Han, Z., Paster, K., Pitis, S., Chan, H., & Ba, J. (2023). Large language models are human-level prompt engineers. The eleventh international conference on learning representations (ICLR 2023). OpenReview. https://openreview.net/forum?id=92gvk82DE-
  19. [19] Yang, C., Wang, X., Lu, Y., Liu, H., Le, Q. V, Zhou, D., & Chen, X. (2024). Large language models as optimizers. International conference on learning representations (Vol. 2024, pp. 12028–12068). OpenReview.net. https://proceedings.iclr.cc/paper_files/paper/2024/file/3339f19c5fcee3ad74502947a32be9e6-Paper-Conference.pdf
  20. [20] Guo, Q., Wang, R., Guo, J., Li, B., Song, K., Tan, X., … ., & Yang, Y. (2024). Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. International conference on learning representations (Vol. 2024, pp. 34133–34156). OpenReview.net. https://proceedings.iclr.cc/paper_files/paper/2024/file/9156b0f6dfa9bbd18c79cc459ef5d61c-Paper-Conference.pdf
  21. [21] Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation, 6(2), 182–197. https://doi.org/10.1109/4235.996017
  22. [22] Lu, Y., Bartolo, M., Moore, A., Riedel, S., & Stenetorp, P. (2022). Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. Proceedings of the 60th annual meeting of the association for computational linguistics (Volume 1: Long papers) (pp. 8086–8098). Dublin, Ireland: Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.acl-long.556
  23. [23] Li, X. L., & Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation. Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (Volume 1: Long papers) (pp. 4582–4597). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.acl-long.353
  24. [24] Lester, B., Al-Rfou, R., & Constant, N. (2021). The power of scale for parameter-efficient prompt tuning. Proceedings of the 2021 conference on empirical methods in natural language processing (pp. 3045–3059). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.emnlp-main.243
  25. [25] Pryzant, R., Iter, D., Li, J., Lee, Y., Zhu, C., & Zeng, M. (2023). Automatic prompt optimization with "gradient descent" and beam search. Proceedings of the 2023 conference on empirical methods in natural language processing (pp. 7957–7968). Singapore: Association for Computational Linguistics. https://doi.org/ 10.18653/v1/2023.emnlp-main.494
  26. [26] Fernando, C., Banarse, D. S., Michalewski, H., Osindero, S., & Rocktäschel, T. (2024). Promptbreeder: Self-referential self-improvement via prompt evolution. Proceedings of the 41st international conference on machine learning (Vol. 235, pp. 13481–13544). PMLR. https://proceedings.mlr.press/v235/fernando24a.html
  27. [27] Feng, S. Y., Gangal, V., Wei, J., Chandar, S., Vosoughi, S., Mitamura, T., & Hovy, E. (2021). A survey of data augmentation approaches for NLP. Findings of the association for computational linguistics: ACL-IJCNLP 2021 (pp. 968–988). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.findings-acl.84
  28. [28] Pires, T., Schlinger, E., & Garrette, D. (2019). How multilingual is multilingual BERT? Proceedings of the 57th annual meeting of the association for computational linguistics (pp. 4996–5001). Florence, Italy: Association for Computational Linguistics. https://doi.org/10.18653/v1/P19-1493
  29. [29] Wu, S., & Dredze, M. (2019). Beto, Bentz, Becas: The surprising cross-lingual effectiveness of BERT. Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP) (pp. 833–844). Hong Kong, China: Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1077
  30. [30] Xue, L., Constant, N., Roberts, A., Kale, M., Al-Rfou, R., Siddhant, A., … ., & Raffel, C. (2021). mT5: A massively multilingual pre-trained text-to-text transformer. Proceedings of the 2021 conference of the north american chapter of the association for computational linguistics: Human language technologies (pp. 483–498). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.naacl-main.41
  31. [31] OpenAI, A. (2023). GPT-4 technical report. https://doi.org/10.48550/arXiv.2303.08774
  32. [32] BigScience Workshop. (2022). Bloom: A 176b-parameter open-access multilingual language model. https://doi.org/10.48550/arXiv.2211.05100
  33. [33] Zhu, W., Liu, H., Dong, Q., Xu, J., Huang, S., Kong, L., … ., & Li, L. (2024). Multilingual machine translation with large language models: Empirical results and analysis. Findings of the association for computational linguistics: NAACL 2024 (pp. 2765–2781). Mexico City, Mexico: Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.findings-naacl.176
  34. [34] Huang, H., Yu, F., Zhu, J., Sun, X., Cheng, H., Dingjie, S., … ., & Xu, J. (2024). AceGPT, localizing large language models in Arabic. Proceedings of the 2024 conference of the north American chapter of the association for computational linguistics: Human language technologies (Volume 1: Long papers) (pp. 8139–8163). Mexico City, Mexico: Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.naacl-long.450
  35. [35] AI Singapore. (2024). SEA-LION: Southeast Asian languages in one network. https://github.com/aisingapore/sealion
  36. [36] Dossou, B. F. P., Tonja, A. L., Yousuf, O., Osei, S., Oppong, A., Shode, I., Awoyomi, O. O., & Emezue, C. C. (2022). AfroLM: A self-active learning-based multilingual pretrained language model for 23 African languages. Proceedings of the third workshop on simple and efficient natural language processing (SustaiNLP) (pp. 52–64). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.sustainlp-1.11
  37. [37] Goldberg, D. E. (1989). Genetic algorithms in search, optimization, and machine learning. Addison-Wesley Longman Publishing. https://dl.acm.org/doi/book/10.5555/534133
  38. [38] Ghareb, A. S., Bakar, A. A., & Hamdan, A. R. (2016). Hybrid feature selection based on enhanced genetic algorithm for text categorization. Expert systems with applications, 49, 31–47. https://doi.org/10.1016/j.eswa.2015.12.004
  39. [39] Smith, T. C., & Witten, I. H. (1995). A genetic algorithm for the induction of natural language grammars. Proceedings of the IJCAI-95 workshop on new approaches to learning for natural language processing (pp. 17–24). Montreal, Canada.
  40. [40] Christy, A., & Thambidurai, P. (2006). Efficient information extraction using machine learning and classification using genetic and C4. 8 algorithms. Information technology journal, 5, 1023–1027. https://doi.org/10.3923/itj.2006.1023.1027
  41. [41] Kirkpatrick, S., Gelatt, C. D., & Vecchi, M. P. (1983). Optimization by simulated annealing. Science, 220(4598), 671–680. https://doi.org/10.1126/science.220.4598.671
  42. [42] Cowie, J., Guthrie, J., & Guthrie, L. (1992). Lexical disambiguation using simulated annealing. COLING 1992: Proceedings of the 14th international conference on computational linguistics (Vol. 1, pp. 359–365). Association for Computational Linguistics. https://doi.org/10.3115/992066.992125
  43. [43] Aliguliyev, R. M. (2009). A new sentence similarity measure and sentence based extractive technique for automatic text summarization. Expert systems with applications, 36(4), 7764–7772. https://doi.org/10.1016/j.eswa.2008.11.022
  44. [44] Germann, U., Jahr, M., Knight, K., Marcu, D., and Yamada, K. (2001). Fast decoding and optimal decoding for machine translation. Proceedings of the 39th annual meeting of the association for computational linguistics (ACL) (pp. 228–235). Association for Computational Linguistics. https://doi.org/10.3115/1073012.1073042
  45. [45] Mahfoud, S. W., & Goldberg, D. E. (1995). Parallel recombinative simulated annealing: A genetic algorithm. Parallel computing, 21(1), 1–28. https://doi.org/10.1016/0167-8191(94)00071-H
  46. [46] Li, W. D., Ong, S. K., & Nee, A. Y. C. (2002). Hybrid genetic algorithm and simulated annealing approach for the optimization of process plans for prismatic parts. International journal of production research, 40(8), 1899–1922. https://doi.org/10.1080/00207540110119991
  47. [47] Ruder, S., Vulić, I., & Søgaard, A. (2019). A survey of cross-lingual word embedding models. Journal of artificial intelligence research, 65, 569–631. https://doi.org/10.1613/jair.1.11640
  48. [48] Pfeiffer, J., Vulić, I., Gurevych, I., & Ruder, S. (2020). MAD-X: An adapter-based framework for multi-task cross-lingual transfer. Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP) (pp. 7654–7673). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.617
  49. [49] Huang, H., Tang, T., Zhang, D., Zhao, X., Song, T., Xia, Y., & Wei, F. (2023). Not all languages are created equal in LLMs: Improving multilingual capability by cross-lingual-thought prompting. Findings of the association for computational linguistics: EMNLP 2023 (pp. 12365–12394). Singapore: Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-emnlp.826
  50. [50] Qin, L., Chen, Q., Wei, F., Huang, S., & Che, W. (2023). Cross-lingual prompting: improving zero-shot chain-of-thought reasoning across languages. Proceedings of the 2023 conference on empirical methods in natural language processing (pp. 2695–2709). Singapore: Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.163
  51. [51] Shi, F., Suzgun, M., Freitag, M., Wang, X., Srivats, S., Vosoughi, S., Chung, H. W., Tay, Y., Ruder, S., Zhou, D., Das, D., & Wei, J. (2023). Language models are multilingual chain-of-thought reasoners. The eleventh international conference on learning representations (ICLR 2023). OpenReview.net. https://dblp.org/rec/conf/iclr/ShiSF0SVCTRZ0W23.html
  52. [52] Winata, G. I., Huang, L., & Vadlamannati, S Chandarana, Y. (2023). Multilingual few-shot learning via language model retrieval. https://doi.org/10.48550/arXiv.2306.10964
  53. [53] Davis, L. (1985). Applying adaptive algorithms to epistatic domains. IJCAI (Vol. 1, pp. 162–164). ACM Digital Library. https://doi.org/10.5555/1625135.1625164
  54. [54] Costa-Jussà, M. R., Cross, J., Çelebi, O., Elbayad, M., Heafield, K., Heffernan, K., … ., & Wang, J. (2022). No language left behind: Scaling human-centered machine translation. https://doi.org/10.48550/arXiv.2207.04672
  55. [55] Batsuren, K., Goldman, O., Khalifa, S., Habash, N., Kieraś, W., Bella, G., … Vylomova, E. (2022). UniMorph 4.0: Universal morphology. Proceedings of the thirteenth language resources and evaluation conference (pp. 840–855). Marseille, France: European Language Resources Association. https://aclanthology.org/2022.lrec-1.89/
  56. [56] Feng, F., Yang, Y., Cer, D., Arivazhagan, N., & Wang, W. (2022). Language-agnostic bert sentence embedding. Proceedings of the 60th annual meeting of the association for computational linguistics (Volume 1: Long papers) (pp. 878–891). Dublin, Ireland: Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.acl-long.62
  57. [57] Črepinšek, M., Liu, S.-H., & Mernik, M. (2013). Exploration and exploitation in evolutionary algorithms: A survey. ACM computing surveys (CSUR), 45(3), 1–33. https://doi.org/10.1145/2480741.2480752
  58. [58] Baly, R., Khaddaj, A., Hajj, H., El-Hajj, W., & Shaban, K. B. (2018). ArSentD-LEV: A multi-topic corpus for target-based sentiment analysis in Arabic levantine tweets. https://doi.org/10.48550/arXiv.1906.01830
  59. [59] Benajiba, Y., Rosso, P., & BenedíRuiz, J. M. (2007). ANERsys: An Arabic named entity recognition system based on maximum entropy. Computational linguistics and intelligent text processing (pp. 143–153). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-70939-8_13
  60. [60] Clark, J. H., Choi, E., Collins, M., Garrette, D., Kwiatkowski, T., Nikolaev, V., & Palomaki, J. (2020). TyDi QA: A benchmark for information-seeking question answering in typologically diverse languages. Transactions of the association for computational linguistics, 8, 454–470. https://doi.org/10.1162/tacl_a_00317
  61. [61] Hasan, T., Bhattacharjee, A., Islam, M. S., Mubasshir, K., Li, Y. F., Kang, Y. B., … ., & Shahriyar, R. (2021). XL-sum: Large-scale multilingual abstractive summarization for 44 languages. Findings of the association for computational linguistics: ACL-IJCNLP 2021 (pp. 4693–4703). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.findings-acl.413
  62. [62] Nguyen, K. Van, Nguyen, V. D., Nguyen, P. X. V, Truong, T. T. H., & Nguyen, N. L. T. (2018). UIT-VSFC: Vietnamese students’ feedback corpus for sentiment analysis. 2018 10th international conference on knowledge and systems engineering (KSE) (pp. 19–24). IEEE. https://doi.org/10.1109/KSE.2018.8573337
  63. [63] Truong, T. H., Dao, M. H., & Nguyen, D. Q. (2021). COVID-19 named entity recognition for vietnamese. Proceedings of the 2021 conference of the north american chapter of the association for computational linguistics: Human language technologies (pp. 2146–2153). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.naacl-main.173
  64. [64] Van Nguyen, K., Nguyen, D. V., Gia-Tuan Nguyen, A., & Luu-Thuy Nguyen, N. (2020). A vietnamese dataset for evaluating machine reading comprehension. Proceedings of the 28th international conference on computational linguistics (pp. 2595–2605). Barcelona, Spain: International Committee on Computational Linguistics. https://doi.org/10.18653/v1/2020.coling-main.233
  65. [65] Muhammad, S. H., Abdulmumin, I., Ayele, A. A., Ousidhoum, N., Adelani, D. I., Yimam, S. M., … ., & Arthur, S. (2023). AfriSenti: A twitter sentiment analysis benchmark for african languages. Proceedings of the 2023 conference on empirical methods in natural language processing (pp. 13968–13981). Singapore: Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.862
  66. [66] Adelani, D. I., Abbott, J., Neubig, G., D’souza, D., Kreutzer, J., Lignos, C., … ., & Osei, S. (2021). MasakhaNER: Named entity recognition for African languages. Transactions of the association for computational linguistics, 9, 1116–1131. https://doi.org/10.1162/tacl_a_00416
  67. [67] Ogundepo, O., Gwadabe, T. R., Rivera, C. E., Clark, J. H., Ruder, S., Adelani, D. I., … ., & Adhiambo, S. (2023). AfriQA: Cross-lingual open-retrieval question answering for african languages. The 2023 conference on empirical methods in natural language processing (EMNLP 2023) (pp. 14957–14972). Singapore: Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-emnlp.997
  68. [68] Kuriyozov, E., & Matlatipov, S. (2019). Building a New Sentiment Analysis Dataset for Uzbek Language and Creating Baseline Models. Proceedings, 21(1), 37. https://doi.org/10.3390/proceedings2019021037
  69. [69] White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., … ., & Schmidt, D. C. (2023). A prompt pattern catalog to enhance prompt engineering with chatgpt. https://doi.org/10.48550/arXiv.2302.11382
  70. [70] Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). LoRA: Low-rank adaptation of large language models. Proceedings of the tenth international conference on learning representations (ICLR 2022). OpenReview.net. https://openreview.net/pdf?id=nZeVKeeFYf9
  71. [71] Lin, C. Y. (2004). ROUGE: A package for automatic evaluation of summaries. Text summarization branches out, 74–81. Association for Computational Linguistics. https://aclanthology.org/W04-1013/
  72. [72] Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2020). BERTScore: Evaluating text generation with BERT. Proceedings of the eighth international conference on learning representations (ICLR 2020). OpenReview.net. https://openreview.net/pdf/15e539377cdf8d827f6e08cb7de3f36a618d824b.pd
  73. [73] Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., … ., & Rush, A. (2020). Transformers: State-of-the-art natural language processing. Proceedings of the 2020 conference on empirical methods in natural language processing: System demonstrations (pp. 38–45). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-demos.6

Published

2026-09-10

Issue

Vol. 3 No. 3 (2026): Metaheuristic Algorithms with Applications (MAA)

Section

Articles

How to Cite

Al-Harthy, A. ., & Thi Lan, N. . (2026). Metaheuristic Optimization of Prompt Structures for Low-Resource Language Models. Metaheuristic Algorithms With Applications, 3(3), 316-340. https://doi.org/10.48313/maa.v3i3.116

Similar Articles

1-10 of 60

You may also start an advanced similarity search for this article.