no code implementations • 4 Feb 2024 • Zifei, Han, Jionghao Lin, Ashish Gurung, Danielle R. Thomas, Eason Chen, Conrad Borchers, Shivang Gupta, Kenneth R. Koedinger
The results indicate that the RAG prompt demonstrated more accurate performance (assessed by the level of hallucination and correctness in the generated assessment texts) and lower financial costs than the other strategies evaluated.
no code implementations • 2 Feb 2024 • Hang Li, Tianlong Xu, Chaoli Zhang, Eason Chen, Jing Liang, Xing Fan, Haoyang Li, Jiliang Tang, Qingsong Wen
The recent surge in generative AI technologies, such as large language models and diffusion models, have boosted the development of AI applications in various domains, including science, finance, and education.
2 code implementations • 3 May 2023 • Eason Chen, Ray Huang, Han-Shin Chen, Yuen-Hsien Tseng, Liang-Yi Li
This paper presents GPTutor, a ChatGPT-powered programming tool, which is a Visual Studio Code extension using the ChatGPT API to provide programming code explanations.
no code implementations • 21 Apr 2023 • Eason Chen
The model considers various factors, including the prompts used for generation; coherence, sentiment, and similarity in the conversation; and users' perceived dialog agents' favorability.
no code implementations • 22 Mar 2023 • Eason Chen
Then we train Big Five classification models with these data and evaluate them with 2500 data from generated dialogues and real conversational datasets labeled in Big Five by human annotators.
no code implementations • 31 Oct 2022 • Eason Chen
Furthermore, according to the effect size of our result, to improve the chatting experience for NLG chatbots which is single reply and anonymous avatar, providing five replies will have more benefits than setting an anime avatar.
no code implementations • 10 Oct 2022 • Eason Chen, Yuen Hsien Tseng, Kuo-Ping Lo
Distance teaching has become popular these years because of the COVID-19 epidemic.
no code implementations • 27 Aug 2022 • Eason Chen, Niall Roche, Yuen-Hsien Tseng, Walter Hernandez, Jiangbo Shangguan, Alastair Moore
This paper proposes a pipeline to automate the SLC creation process with several Natural Language Processing (NLP) models to convert law contracts to the Accord Project's Concerto model.