[3M1-OS-12a] OS-12

[3M1-OS-12a-05] A study on the influence of generative AI on political information issues

NTCIR-14 QA Lab PoliInfo task as an example

〇Hideyuki Shibuki¹, Yasuhiro Ogawa², Yasutomo Kimura³, Hokuto Ototake⁴, Yuzu Uchida⁵, Keiichi Takamaru⁶, Kazuma Kadowaki⁷, Tomoyoshi Akiba⁸, Minoru Sasaki⁹, Akio Kobayashi¹⁰ (1. BESNA Institute Inc., 2. Nagoya City University, 3. Otaru University of Commerce, 4. Fukuoka University, 5. Hokkai-Gakuen University, 6. Utsunomiya Kyowa University, 7. The Japan Research Institute, Limited, 8. Toyohashi University of Technology, 9. Ibaraki University, 10. National Agriculture and Food Research Organization)

Keywords:NLP, LLM, political information, summarization, QA Lab PoliInfo

With the rise of generative AI such as ChatGPT, natural language processing has changed significantly. We have been holding shared tasks on political information issues since before the rise. In this paper, we present the results of solving the tasks at that time using generative AI, and consider the impact that generative AI has had on solving political information issues.