Publications

Note: Underline denotes equal contribution.

Journals

2024

  1. Pittawat Taveekitworachai, Gunt Chanmas, Pujana Paliyawan, Ramita Thawonmas, Chakarida Nukoolkit, Piyapat Dajpratham, and Ruck Thawonmas, "A Systematic Review of Major Evaluation Metrics for Simulator-Based Automatic Assessment of Driving after Stroke." Heliyon 9, e32930 (2024).

    Simulator-based Driving Assessment
    Post-Stroke Driving

  2. Febri Abdullah, Pittawat Taveekitworachai, Mury F. Dewantoro, Ruck Thawonmas, Julian Togelius, and Jochen Renz. "The 1st ChatGPT4PCG Competition." IEEE Transactions on Games (2024).

    Large Language Models
    Prompt Engineering
    Procedural Content Generation
    Level Generation
    LLM Evaluation

2023

  1. Gunt Chanmas, Pittawat Taveekitworachai, Pujana Paliyawan, Ramita Thawonmas, Ruck Thawonmas, Chakarida Nukoolkit, and Piyapat Dajpratham. "Driving scenarios and environmental settings in simulator-based driving assessment systems for stroke: a systematic review." Topics in stroke rehabilitation 30.8 (2023): 872-880.

    Simulator-based Driving Assessment
    Post-Stroke Driving

Conferences

2024

  1. Pittawat Taveekitworachai, Kantinan Plupattanakit, and Ruck Thawonmas "Assessing Inherent Biases Following Prompt Compression of Large Language Models for Game Story Generation." Accepted at 2024 IEEE Conference on Games (CoG 2024). 2024. [Research artifacts]

    Large Language Models
    Prompt Engineering
    Prompt Compression
    Biases
    Procedural Content Generation
    Story Generation
    LLM Evaluation

  2. Pittawat Taveekitworachai, Yi Xia, Pratch Suntichaikul, and Ruck Thawonmas "Towards LLM4PCG: A Preliminary Evaluation of Open-Weight Large Language Models Beyond ChatGPT4PCG." Accepted at 2024 IEEE Conference on Games (CoG 2024). 2024. [Research artifacts 1, Research artifacts 2]

    Large Language Models
    Prompt Engineering
    Procedural Content Generation
    Level Generation
    LLM Evaluation

  3. Pittawat Taveekitworachai, Febri Abdullah, Mury F. Dewantoro, Yi Xia, Pratch Suntichaikul, Ruck Thawonmas, Julian Togelius, and Jochen Renz. "ChatGPT4PCG 2 Competition: Prompt Engineering for Science Birds Level Generation." Accepted at 2024 IEEE Conference on Games (CoG 2024). 2024. [Research artifacts]

    Large Language Models
    Prompt Engineering
    Procedural Content Generation
    Level Generation
    LLM Evaluation

  4. Xiao You, Pittawat Taveekitworachai, Siyuan Chen, Mustafa Can Gursesli, Xiaoxu Li, Yi Xia and Ruck Thawonmas. "Dragons, and Emotions: A Preliminary Study of Player Sentiment in LLM-driven TTRPGs." Proceedings of the 19th International Conference on the Foundations of Digital Games. 2024.

    Large Language Models
    LLM-Powered Games
    Tabletop RPGs
    Prompt Engineering
    Peronsality Prompting

  5. Pittawat Taveekitworachai, Pratch Suntichaikul, Chakarida Nukoolkit, and Ruck Thawonmmas. "Speed Up! Cost-Effective Large Language Model for ADAS Via Knowledge Distillation." Proceedings of the 2024 IEEE Intelligent Vehicles Symposium (IV 2024). IEEE, 2024. [Research artifacts]

    Large Language Models
    Knowledge Distillation
    Efficient LLMs
    Prompt Engineering
    Vector Database
    Advanced Driver-Assistance System
    LLM Evaluation

  6. Pittawat Taveekitworachai, Febri Abdullah, Mustafa Can Gursesli, Antonio Lanata, Andrea Guazzini, and Ruck Thawonmmas. "Prompt Evolution Through Examples for Large Language Models—A Case Study in Game Comment Toxicity Classification." Proceedings of the 2024 IEEE International Workshop on Metrology for Industry 4.0 & IoT. IEEE, 2024. [Research artifacts]

    Large Language Models
    Prompt Engineering
    Automatic Prompt Optimization
    Errorful Learning
    Evolutionary Computation
    Toxicity Classification
    LLM Evaluation

2023

  1. Pittawat Taveekitworachai and Ruck Thawonmas. "Enhancing Novelty in ChatGPT Responses: Incorporating Random Word Brainstorming." Proceedings of the 13th International Conference on Advances in Information Technology. 2023. [Research artifacts]

    Large Language Models
    Prompt Engineering
    Creavitity in LLMs
    Random Word Brainstorming

  2. Chollakorn Nimpattanavong, Pittawat Taveekitworachai, Ibrahim Khan, Thai Van Nguyen, Ruck Thawonmas, Worawat Choensawat, and Kingkarn Sookhanaphibarn. "Am I Fighting Well? Fighting Game Commentary Generation With ChatGPT." Proceedings of the 13th International Conference on Advances in Information Technology. 2023. [Research artifacts]

    Large Language Models
    LLM Evaluation
    Prompt Engineering
    Game Commentary Generation

  3. Pittawat Taveekitworachai, Febri Abdullah, Mury F. Dewantoro, Ruck Thawonmas, Julian Togelius, and Jochen Renz. "ChatGPT4PCG Competition: Character-like Level Generation for Science Birds." 2023 IEEE Conference on Games (CoG). IEEE, 2023. [Research artifacts]

    Large Language Models
    Prompt Engineering
    Procedural Content Generation
    Level Generation
    LLM Evaluation

  4. Pittawat Taveekitworachai, Febri Abdullah, Mustafa Can Gursesli, Mury F. Dewantoro, Siyuan Chen, Antonio Lanata, Andrea Guazzini, and Ruck Thawonmmas. "What Is Waiting for Us at the End? Inherent Biases of Game Story Endings in Large Language Models." International Conference on Interactive Digital Storytelling. Cham: Springer Nature Switzerland, 2023. [Research artifacts]

    Large Language Models
    Biases in LLMs
    Procedural Content Generation
    Story Generation
    LLM Evaluation
    Sentiment Analysis

  5. Pittawat Taveekitworachai, Febri Abdullah, Mustafa Can Gursesli, Mury F. Dewantoro, Siyuan Chen, Antonio Lanata, Andrea Guazzini, and Ruck Thawonmmas. "Breaking bad: Unraveling Influences and Risks of User Inputs to ChatGPT for Game Story Generation." International Conference on Interactive Digital Storytelling. Cham: Springer Nature Switzerland, 2023. [Research artifacts]

    Large Language Models
    Risks in LLMs
    Procedural Content Generation
    Story Generation
    Adversarial Prompting
    LLM Evaluation
    Sentiment Analysis

  6. Mustafa Can Gursesli, Pittawat Taveekitworachai, Febri Abdullah, Mury F. Dewantoro, Antonio Lanata, Andrea Guazzini, and Ruck Thawonmmas. "The Chronicles of ChatGPT: Generating and Evaluating Visual Novel Narratives on Climate Change Through ChatGPT." International Conference on Interactive Digital Storytelling. Cham: Springer Nature Switzerland, 2023. [Research artifacts]

    Large Language Models
    Prompt Engineering
    Procedural Content Generation
    Story Generation
    LLM Evaluation
    Visual Novels

  7. Xiaoxu Li, Xiao You, Siyuan Chen, Pittawat Taveekitworachai, and Ruck Thawonmmas. "Analyzing Audience Comments: Improving Interactive Narrative with ChatGPT." International Conference on Interactive Digital Storytelling. Cham: Springer Nature Switzerland, 2023.

    Large Language Models
    Audience Participation Games
    Text Classification
    LLM Evaluation

  8. Pittawat Taveekitworachai, Mustafa Can Gursesli, Febri Abdullah, Siyuan Chen, Federico Cala, Andrea Guazzini, Antonio Lanata, and Ruck Thawonmmas. "Journey of ChatGPT from Prompts to Stories in Games: the Positive, the Negative, and the Neutral." 2023 IEEE 13th International Conference on Consumer Electronics-Berlin (ICCE-Berlin). IEEE, 2023. [Research artifacts]

    Large Language Models
    Biases in LLMs
    Procedural Content Generation
    Story Generation
    LLM Evaluation
    Sentiment Analysis

2022

  1. Pittawat Taveekitworachai, and Jonathan H. Chan. "Krathu-500: Post-Comments Thai Corpus." 2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C). IEEE, 2022. [Research artifacts]

    Natural Language Processing Datasets
    Thai
    Sentiment Analysis

Preprints

2024

  1. Pittawat Taveekitworachai, Febri Abdullah, and Ruck Thawonmas. "Large Language Models are Null-Shot Learners." arXiv preprint arXiv:2401.08273 (2024).

    Large Language Models
    Prompt Engineering
    Null-Shot Prompting
    Hallucination in LLMs
    LLM Evaluation

  2. Gunt Chanmas, Pittawat Taveekitworachai, Xiao You, Ruck Thawonmas, Chakarida Nukoolkit, and Piyapat Dajpratham, "Driving Assistant Using ChatGPT Pre-Generated Messages in Simulator-Based Driving Assessment: Toward Low-Cost Driving Assessment for Stroke Patients." SSRN 4711961 (2024).

    Large Language Models
    Efficient LLMs
    Prompt Engineering
    Vector Database
    Simulator-based Driving Assessment