PETEPITTAWAT.DEV - Publications

Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe

Kunat Pipatanakul, Pittawat Taveekitworachai, Potsawee Manakul, Kasima Tharnpipitchai

Conference

International Conference on Learning Representations (ICLR) - Open Science for Foundation Models (SCI-FM) 2025 Workshop2025

Large Language Models

Reasoning Models

Model Merging

Paper Typhoon R1 (Research Preview)

BenchING: A Benchmark for Evaluating Large Language Models in Following Structured Output Format Instruction in Text-Based Narrative Game Tasks

Pittawat Taveekitworachai, Mury F. Dewantoro, Yi Xia, Pratch Suntichaikul, Ruck Thawonmas

Journal

IEEE Transactions on Games2025

First author

Large Language Models

Prompt Engineering

Procedural Content Generation

LLM Evaluation

Paper Code

FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning

Natapong Nitarach, Warit Sirichotedumrong, Panop Pitchayarthorn, Pittawat Taveekitworachai, Potsawee Manakul, Kunat Pipatanakul

Preprint

arXiv2025

Large Language Models

Prompt Engineering

Reasoning Models

Paper

Prior Prompt Engineering for Reinforcement Fine-Tuning

Pittawat Taveekitworachai, Potsawee Manakul, Sarana Nutanong, Kunat Pipatanakul

Conference

The Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025, Main2025

First author

Large Language Models

Prompt Engineering

Reinforcement Learning

Reinforcement Fine-Tuning

Reasoning Models

Prior Prompts

Paper

The Role of Large Language Model-Generated Stories in the Narrative Experience of Serious Visual Novel Games

Mustafa Can Gursesli, Siyuan Chen, Mury Fajar Dewantoro, Xiao You, Ege Anbar, Pittawat Taveekitworachai, Febri Abdullah, Pietro Tarchi, Mirko Duradoni, Antonio Lanata, Andrea Guazzini, Ruck Thawonmas

Journal

International Journal of Human–Computer Interaction2025

Large Language Models

Prompt Engineering

Procedural Content Generation

Visual Novels

HCI

Paper

Typhoon T1: An Open Thai Reasoning Model

Pittawat Taveekitworachai, Potsawee Manakul, Kasima Tharnpipitchai, Kunat Pipatanakul

Conference

International Conference on Learning Representations (ICLR) - Open Science for Foundation Models (SCI-FM) 2025 Workshop2025

First author

Large Language Models

Reasoning Models

Supervised Fine-Tuning

Paper Typhoon T1 (Research Preview)

A Systematic Review of Major Evaluation Metrics for Simulator-Based Automatic Assessment of Driving after Stroke

Pittawat Taveekitworachai, Gunt Chanmas, Pujana Paliyawan, Ramita Thawonmas, Chakarida Nukoolkit, Piyapat Dajpratham, Ruck Thawonmas

Journal

Heliyon Vol. 10, Issue 12, E329302024

First author

Simulator-based Driving Assessment

Post-Stroke Driving

Paper

Assessing Inherent Biases Following Prompt Compression of Large Language Models for Game Story Generation

Pittawat Taveekitworachai, Kantinan Plupattanakit, Ruck Thawonmas

Conference

IEEE Conference on Games (CoG) 20242024

First author

Large Language Models

Prompt Engineering

Prompt Compression

Biases

Procedural Content Generation

Story Generation

LLM Evaluation

Paper Research artifacts

ChatGPT4PCG 2 Competition: Prompt Engineering for Science Birds Level Generation

Pittawat Taveekitworachai, Febri Abdullah, Mury F. Dewantoro, Yi Xia, Pratch Suntichaikul, Ruck Thawonmas, Julian Togelius, Jochen Renz

Conference

IEEE Conference on Games (CoG) 20242024

First author

Large Language Models

Prompt Engineering

Procedural Content Generation

Level Generation

LLM Evaluation

Paper Research artifacts

Don't Do That! Reverse Role Prompting Helps Large Language Models Stay in Personality Traits

Siyuan Chen, Pittawat Taveekitworachai, Yi Xia, Xiaoxu Li, Mustafa Can Gursesli, Antonio Lanata, Andrea Guazzini, Ruck Thawonmas

Conference

International Conference on Interactive Digital Storytelling (ICIDS) 20242024

Role Prompting

Reverse Role Prompting

Large Language Models

Game Story Generation

Biases

LLM Evaluation

Paper

Driving Assistant Using Generative AI Pre-generated Messages in Simulator-Based Driving Assessment: A Step Towards Low-Cost Simulator-Based Driving Assessment

Gunt Chanmas, Pittawat Taveekitworachai, Xiao You, Ruck Thawonmas, Chakarida Nukoolkit, Piyapat Dajpratham

Journal

Heliyon Vol. 10, Issue 16, E359412024

Simulator-based Driving Assessment

Post-Stroke Driving

Large Language Models

Vector Database

Efficient LLMs

Paper

Dungeons, Dragons, and Emotions: A Preliminary Study of Player Sentiment in LLM-driven TTRPGs

Xiao You, Pittawat Taveekitworachai, Mustafa Can Gursesli, Xiaoxu Li, Yi Xia, Ruck Thawonmas

Conference

ACM International Conference on the Foundations of Digital Games (FDG) 20242024

Large Language Models

LLM-Powered Games

Tabletop RPGs

Prompt Engineering

Peronsality Prompting

Paper

Publications

Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe

BenchING: A Benchmark for Evaluating Large Language Models in Following Structured Output Format Instruction in Text-Based Narrative Game Tasks

FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning

Prior Prompt Engineering for Reinforcement Fine-Tuning

The Role of Large Language Model-Generated Stories in the Narrative Experience of Serious Visual Novel Games

Typhoon T1: An Open Thai Reasoning Model

A Systematic Review of Major Evaluation Metrics for Simulator-Based Automatic Assessment of Driving after Stroke

Assessing Inherent Biases Following Prompt Compression of Large Language Models for Game Story Generation

ChatGPT4PCG 2 Competition: Prompt Engineering for Science Birds Level Generation

Don't Do That! Reverse Role Prompting Helps Large Language Models Stay in Personality Traits

Driving Assistant Using Generative AI Pre-generated Messages in Simulator-Based Driving Assessment: A Step Towards Low-Cost Simulator-Based Driving Assessment

Dungeons, Dragons, and Emotions: A Preliminary Study of Player Sentiment in LLM-driven TTRPGs

Academic Services

Conferences

Journals