プレプリント / バージョン1

対話型生成AIにおける質問スタイルが応答特性に与える影響:丁寧な表現と直接的な表現のコミュニケーションパターンの比較分析

##article.authors##

  • 佐藤, 桂輔 茨城工業高等専門学校 一般教養部

DOI:

https://doi.org/10.51094/jxiv.966

キーワード:

生成AI、 質問スタイル、 プロンプトエンジニアリング、 対話の解析

抄録

本研究では、質問スタイルが生成AIとの対話に与える影響を実験的手法により検証しました。特に、丁寧で配慮的なコミュニケーションスタイル(タイプA)と、直接的で簡潔なコミュニケーションスタイル(タイプD)という対照的な質問パターンに着目し、これらが生成AIの応答特性にもたらす影響を分析しました。実験では、ChatGPT、Claude、Command R+、Geminiという4つの主要な生成AIモデルを対象に、画像生成AIに関する技術的説明をテーマとした対話を実施しました。

分析の結果、質問スタイルの違いがAIの応答生成プロセスに大きな影響を及ぼすことが明らかになりました。配慮表現を含む問いかけは包括的で体系的な応答を引き出し、直接的な質問は簡潔で焦点を絞った応答を導く傾向が示されました。この影響は、単なる表現の表層的な違いを超えて、情報の構造化の仕方や学習プロセスにまで及ぶことが注目に値します。具体的には、タイプAの質問は文脈構築型の情報構造と探究型の学習パターンを促進し、タイプDの質問は補完型の構造と集中型の学習パターンを促進することが観察されました。

これらの知見は、生成AIとの効果的な対話方法の確立に重要な示唆を与えています。特に、教育・学習環境におけるAI活用や、組織におけるAIリテラシー教育の設計において、目的に応じた質問スタイルの戦略的選択の重要性を浮き彫りにしています。本研究は、AI時代における人間とAIのコミュニケーションの質的向上に寄与する基礎的な洞察を提供しています。

利益相反に関する開示

本研究に関連して開示すべき利益相反はありません。

ダウンロード *前日までの集計結果を表示します

ダウンロード実績データは、公開の翌日以降に作成されます。

引用文献

Rahimi, F., Talebi Bezmin Abadi, A.: Chatgpt and publication ethics. Archives of Medical Research 54(3), 272-274 (2023) https://doi.org/10.1016/j.arcmed.2023.03.004

Bick, A., Blandin, A., Deming, D.J.: The rapid adoption of generative ai. Working Paper 32966, National Bureau of Economic Research (September 2024). https://doi.org/10.3386/w32966 . http://www.nber.org/papers/w32966

Namoun, A., Ibrahim, I.A., Mustafa, E., Alrehaili, A., more: Generative artificial intelligence in education: an umbrella review of applications and challenges. Research Square (2024) https://doi.org/10.21203/rs.3.rs-8498155/v2 . This is a preprint; it has not been peer-reviewed by a journal

Bozkurt, A.: Tell me your prompts and I will make them true: The alchemy of prompt engineering and generative AI. International Council for Open and Distance Education Oslo, Norway (2024). https://doi.org/10.55982/openpraxis.16.2.661

White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., Schmidt, D.C.: A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT (2023). https://arxiv.org/abs/2302.11382

Chen, B., Zhang, Z., Langrené, N., Zhu, S.: Unleashing the potential of prompt engineering in large language models: a comprehensive review. arXiv preprint arXiv:2310.14735 (2023)

Markowitz, D.M., Boyd, R.L., Blackburn, K.: From silicon to solutions: AI's impending impact on research and discovery. Frontiers in Social Psychology 2 (2024) https://doi.org/10.3389/frsp.2024.1392128

Alafnan, M.A., Dhari, S., Jovic, M., Lomidz, K.: Chatgpt as an educational tool: Opportunities, challenges, and recommendations for communication, business writing, and composition courses. Journal of Artificial Intelligence and Technology 3(2), 60-64 (2023) https://doi.org/10.37965/jait.2023.00184

Degraa, I., Chamari, K., Zmijewski, P., Ben Saad, H.: From human writing to artificial intelligence generated text: examining the prospects and potential threats of chatgpt in academic writing. Biology of Sport 40(2), 615-622 (2023) https://doi.org/10.5114/biolsport.2023.125623

Kestin, G., Miller, K., Kiales, A., Milbourne, T., Ponti, G.: Ai tutoring outperforms active learning. Research Square (2024) https://doi.org/10.21203/rs.3.rs-4243877/v1 . Preprint

Sok, S., Heng, K.: Opportunities, challenges, and strategies for using chatgpt in higher education: A literature review. Journal of Digital Educational Technology 4(1), 2401 (2024) https://doi.org/10.30935/jdet/14027

Cotton, D.R.E., Cotton, P.A., Shipway, J.R.: Chatting and cheating: Ensuring academic integrity in the era of chatgpt. Innovations in Education and Teaching International 61(2), 228-239 (2023) https://doi.org/10.1080/14703297.2023.2190148

Crawford, J., Cowling, M., Allen, K.-A.: Leadership is needed for ethical chatgpt: Character, assessment, and learning using artificial intelligence (ai). Journal of University Teaching & Learning Practice 20(3) (2023) https://doi.org/10.53761/1.20.3.02

Jarrah, A.M., Wardat, Y., Fidalgo, P.: Using chatgpt in academic writing is (not) a form of plagiarism: What does the literature say? Online Journal of Communication and Media Technologies 13(4), 202346 (2023) https://doi.org/10.30935/ojcmt/13572

Karakose, T.: The utility of chatgpt in educational research—potential opportunities and pitfalls. Educational Process: International Journal 12(2), 7-13 (2023) https://doi.org/10.22521/edupij.2023.122.1

Rasul, T., Nair, S., Kalendra, D., Robin, M., Santini, F.d.O., Ladeira, W.J., Sun, M., Day, I., Rather, R.A., Heathcote, L.: The role of chatgpt in higher education: Benefits, challenges, and future research directions. Journal of Applied Learning & Teaching 6(1) (2023) https://doi.org/10.37074/jalt.2023.6.1.29

Elsen-Rooney, M.: NYC Education Department Blocks ChatGPT on School Devices, Networks. Chalkbeat New York. Accessed: 2023-01-04. https://www.chalkbeat.org/2023/1/4/23538888/nyc-schools-blocks-chatgpt-artificial-intelligence

Korzyński, P., Mazurek, G., Krzypkowska, P., Kurasiński, A.: Artificial intelligence prompt engineering as a new digital competence: Analysis of generative ai technologies such as chatgpt. Entrepreneurial Business and Economics Review (2023) https://doi.org/10.15678/eber.2023.110302

Wu, S., Shen, X., Xia, R.: A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentions (2023). https://arxiv.org/abs/2310.03293

Tix, B.J.: Follow-Up Questions Improve Documents Generated by Large Language Models (2024). https://arxiv.org/abs/2407.12017

Sabzalieva, E., Valentini, A.: Chatgpt and artificial intelligence in higher education: quick start guide. Technical report, International Institute for Higher Education in Latin America and the Caribbean (IESALC) (2023). United Nations Educational, Scientific and Cultural Organization (UNESCO). Accessed: 2023-04. https://eduq.info/xmlui/handle/11515/38828

Malik, A., Khan, M.L., Hussain, K.: How is chatgpt transforming academia? examining its impact on teaching, research, assessment, and learning. Technical report, Sultan Qaboos University (April 9 2023). https://doi.org/10.2139/ssrn.4413516 . SSRN Electronic Journal, Last revised: November 10, 2024. https://ssrn.com/abstract=4413516

Mizumoto, T., Yamazaki, T., Yoshikawa, K., Ohagi, M., Kawamoto, T., Sato, T.: Dialogue systems can generate appropriate responses without the use of question marks? - a study of the effects of "?" for spoken dialogue systems -. In: Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S., Xue, N. (eds.) Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 4858-4864. ELRA and ICCL, Torino, Italia (2024). https://aclanthology.org/2024.lrec-main.435

Li, J.: Teaching Machines to Converse (2020). https://arxiv.org/abs/2001.11701

Noever, D., McKee, F.: Chatbots as Problem Solvers: Playing Twenty Questions with Role Reversals (2023). https://arxiv.org/abs/2301.01743

Oppenlaender, J., Linder, R., Silvennoinen, J.: Prompting AI Art: An Investigation into the Creative Skill of Prompt Engineering (2024). https://arxiv.org/abs/2303.13534

Boussioux, L., Lane, J.N., Zhang, M., Jacimovic, V., Lakhani, K.R.: The crowdless future? generative ai and creative problem-solving. Organization Science 35(5), 1589-1607 (2024) https://doi.org/10.1287/orsc.2023.1843 https://doi.org/10.1287/orsc.2023.1843

Sato, K.: The effect of question formats in dialogue with generative ai: A comparative analysis of open questions and prompt engineering. Jxiv (2024) https://doi.org/10.51094/jxiv.853 . Version 1

Motoki, F., Neto, V.P., Rodrigues, V.: More human than human: measuring chatgpt political bias. Public Choice 198(1), 3-23 (2024) https://doi.org/10.1007/s11127-023-01097-2

ダウンロード

公開済


投稿日時: 2024-11-21 06:36:07 UTC

公開日時: 2024-11-22 10:08:20 UTC
研究分野
情報科学