WisdomBot: Tuning Large Language Models with Artificial Intelligence Knowledge

Abstract

Large language models (LLMs) have emerged as powerful tools in natural language processing (NLP), showing a promising future of artificial generated intelligence (AGI). Despite their notable performance in the general domain, LLMs have remained suboptimal in the field of education, owing to the unique challenges presented by this domain, such as the need for more specialized knowledge, the requirement for personalized learning experiences, and the necessity for concise explanations of complex concepts. To address these issues, this paper presents a novel LLM for education named WisdomBot, which combines the power of LLMs with educational theories, enabling their seamless integration into educational contexts. To be specific, we harness self-instructed knowledge concepts and instructions under the guidance of Bloom’s Taxonomy as training data. To further enhance the accuracy and professionalism of model’s response on factual questions, we introduce two key enhancements during inference, i.e., local knowledge base retrieval augmentation and search engine retrieval augmentation during inference. We substantiate the effectiveness of our approach by applying it to several Chinese LLMs, thereby showcasing that the fine-tuned models can generate more reliable and professional responses.

Graphical abstract

Keywords

artificial intelligence (AI) / large language models (LLMs) / intelligent education

References

[1] KrathwohlD. R.. (2002). A Revision of Bloom’s Taxonomy: An Overview. Theory Into Practice, 41(4), 212–218.

[2] BaiJ., Bai, S., Chu, Y., Cui, Z., Dang, K., Deng, X., Fan, Y., Ge, W., Han, Y., Huang, F., Hui, B., Ji, L., Li, M., Lin, J., Lin, R., Liu, D., Liu, G., Lu, C., Lu, K., Ma, J., Men, R., Ren, X., Ren, X., Tan, C., Tan, S., Tu, J., Wang, P., Wang, S., Wang, W., Wu, S., Xu, B., Xu, J., Yang, A., Yang, H., Yang, J., Yang, S., Yao, Y., Yu, B., Yuan, H., Yuan, Z., Zhang, J., Zhang, X., Zhang, Y., Zhang, Z., Zhou, C., Zhou, J., Zhou, X., &ZhuT.. (2023). Qwen technical report. arXiv Preprint, arXiv:2309.16609.

[3] Baidoo-Anu D., &Owusu Ansah L. (2023). Education in the era of generative artificial intelligence (AI): Understanding the potential benefits of ChatGPT in promoting teaching and learning.Journal of AI, 7(1): 52–62

[4] BloomB. S., Engelhart, M. D., Furst, E. J., Hill, W. H., &KrathwohlD. R.. (1956). Handbook I: Cognitive domain. New York: David McKay.

[5] CaoB., Lin, H., Han, X., Sun, L., Yan, L., Liao, M., Xue, T., &XuJ.. (2021). Knowledgeable or educated guess? Revisiting language models as knowledge bases. In: 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). Online: Association for Computational Linguistics, 1860–1874.

[6] CuiY., Yang, Z., &YaoX.. (2023). Efficient and effective text encoding for Chinese LLaMA and Alpaca. arXiv Preprint, arXiv:2304.08177.

[7] ElsayedS.. (2023). Towards mitigating ChatGPT’s negative impact on education: Optimizing question design through Bloom’s Taxonomy. In: Proceedings of 2023 IEEE Region 10 Symposium (TENSYMP). Canberra, 1–6.

[8] HuE., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., &ChenW.. (2021). LoRA: Low-rank adaptation of large language models. arXiv Preprint, arXiv:2106.09685v2.

[9] HuangY., Bai, Y., Zhu, Z., Zhang, J., Zhang, J., Su, T., Liu, J., Lv, C., Zhang, Y., Lei, J., Fu, Y., Sun, M., &HeJ.. (2024). C-Eval: A multi-level multi-discipline Chinese evaluation suite for foundation models. Advances in Neural Information Processing Systems, 36.

[10] LiuH., Ning, R., Teng, Z., Liu, J., Zhou, Q., &ZhangY.. (2023). Evaluating the logical reasoning ability of ChatGPT and GPT-4. arXiv Preprint, arXiv:2304.03439.

[11] OpenAI. (2023). GPT-4 technical report. arXiv Preprint, arXiv:2303.08774.

[12] Ouyang L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P. F., Leike, J., &Lowe R. (2022). Training language models to follow instructions with human feedback.Advances in Neural Information Processing Systems, 35: 27730–27744

[13] Ramirez T. V. (2017). On pedagogy of personality assessment: Application of Bloom’s Taxonomy of educational objectives.Journal of Personality Assessment, 99(2): 146–152

[14] TaoriR., Gulrajani, I., Zhang, T., Dubois, Y., Li, X., Guestrin, C., Liang, P., &HashimotoT. B.. (2023). Stanford Alpaca: An instruction-following LLaMA model. Retrieved from GitHub.

[15] TouvronH., Lavril, T., Izacard, G., Martinet, X., Lachaux, M. A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., &LampleG.. (2023). LLaMA: Open and efficient foundation language models. arXiv Preprint, arXiv:2302.13971.

[16] WangC., Liu, P., &ZhangY.. (2021). Can generative pre-trained language models serve as knowledge bases for closed-book QA? In: 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). Online: Association for Computational Linguistics, 3241–3251.

[17] WangY., Kordi, Y., Mishra, S., Liu, A., Smith, N. A., Khashabi, D., &HajishirziH.. (2023). Self-instruct: Aligning language models with self-generated instructions. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Toronto: Association for Computational Linguistics, 13484–13508.

[18] WeiJ., Bosma, M., Zhao, V., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., &LeQ. V.. (2021). Finetuned language models are zero-shot learners. arXiv Preprint, arXiv:2109.01652v2.

[19] YangL., Chen, H., Li, Z., Ding, X., &WuX.. (2023). ChatGPT is not enough: Enhancing large language models with knowledge graphs for fact-aware language modeling. arXiv Preprint, arXiv:2306.11489.

[20] ZengA., Liu, X., Du, Z., Wang, Z., Lai, H., Ding, M., Yang, Z., Xu, Y., Zheng, W., Xia, X., Tam, W. L., Ma, Z., Xue, Y., Zhai, J., Chen, W., Liu, Z., Zhang, P., Dong, Y., &TangJ.. (2022). GLM-130B: An open bilingual pre-trained model. arXiv Preprint, arXiv:2210.02414v2.

Acknowledgments

This work was supported by the National Science and Technology Major Project, China (Grant No. 2022ZD0117104), the National Natural Science Foundation of China (Grant Nos. 62037001 and 62307032), and the Starry Night Science Fund at Shanghai Institute for Advanced Study (SN-ZJU-SIAS-0010).

Conflict of Interest

Fei Wu is a member of the Editorial Board of Frontiers of Digital Education, who was excluded from the peer-review process and all editorial decisions related to the acceptance and publication of this article. Peer-review was handled independently by the other editors to minimise bias.

RIGHTS & PERMISSIONS

2024 Higher Education Press