Research Record

Publications

Papers on prompting, reasoning, evaluation, generative systems, and applied AI across research and domain collaborations.

PublicationPreprint2026
Exploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code Interpreter
Patomporn PayoungkhamdeeNapat Laosaengpha
Venue
Published in arXiv.
Large Language Models
Code Interpreter
Tool-Integrated Reasoning
Post-Training
Paper

PublicationConference2026
Extending Audio Context for Long-Form Understanding in Large Audio-Language Models
Yuatyong ChaichanaPittawat Taveekitworachai (co-advisor)
Venue
Published in The Conference of the European Chapter of the Association for Computational Linguistics 2026 (EACL 2026), Main.
Large Audio Language Models
Long Context
PaperGitHub
PublicationPreprint2026
Formula-One Prompting: Adaptive Reasoning Through Equations For Applied Mathematics
Natapong NitarachPittawat TaveekitworachaiKunat Pipatanakul
Venue
Published in arXiv.
Large Language Models
Prompt Engineering
Finance
Paper
PublicationPreprint2026
On the Robustness of Answer Formats in Medical Reasoning Models
Pittawat Taveekitworachai (co-first author)Natpatchara Pongjirapat (co-first author)
Venue
Published in arXiv.
Large Language Models
Medical AI
Reasoning Models
PaperTyphoon-Si-Med-Thinking-4B (Research Preview)
PublicationPreprint2026
Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition
Warit SirichotedumrongAdisai Na-Thalang
Venue
Published in arXiv.
Automatic Speech Recognition
Streaming ASR
Paper
PublicationPreprint2026
Typhoon OCR: Open Vision-Language Model For Thai Document Extraction
Surapon NonesungNatapong Nitarach
Venue
Published in arXiv.
Optical Character Recognition
Vision-Language Models
Paper
PublicationPreprint2026
Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models
Kunat PipatanakulPittawat Taveekitworachai
Venue
Published in arXiv.
Large Language Models
Thai Language
PaperTyphoon S
PublicationConference2026
Wait, Do We Need to Wait? Revisiting Budget Forcing for Sequential Test-Time Scaling
Pittawat TaveekitworachaiKunat Pipatanakul
Venue
Published in The International Conference on Learning Representations (ICLR) 2026, Blog Post Track.
Large Language Models
Test-Time Scaling
Instruction Following
PaperResearch artifacts
PublicationPreprint2026
When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models
Pakhapoom SarapatSaksorn Ruangtanusak
Venue
Published in arXiv.
Large Language Models
Reasoning Models
Paper
PublicationConference2025
Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
Kunat PipatanakulPittawat Taveekitworachai
Venue
Published in International Conference on Learning Representations (ICLR) - Open Science for Foundation Models (SCI-FM) 2025 Workshop.
Large Language Models
Reasoning Models
Model Merging
PaperTyphoon R1 (Research Preview)
PublicationJournal2025
BenchING: A Benchmark for Evaluating Large Language Models in Following Structured Output Format Instruction in Text-Based Narrative Game Tasks
Pittawat TaveekitworachaiMury F. Dewantoro
Venue
Published in IEEE Transactions on Games.
Large Language Models
Prompt Engineering
PaperCode
PublicationConference2025
FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning
Natapong NitarachWarit Sirichotedumrong
Venue
Published in The 10th Workshop on Financial Technology and Natural Language Processing (FinNLP - ACL SIGFin) (Oral), EMNLP 2025.
Large Language Models
Prompt Engineering
Reasoning Models
Paper
PublicationConference2025
Prior Prompt Engineering for Reinforcement Fine-Tuning
Pittawat TaveekitworachaiPotsawee Manakul
Venue
Published in The Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025, Main.
Large Language Models
Prompt Engineering
Paper
PublicationConference2025
Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
Saksorn RuangtanusakPittawat TaveekitworachaiKunat Pipatanakul
Venue
Published in The 5th Wordplay: When Language Meets Games Workshop (Spotlight), EMNLP 2025.
Large Language Models
Prompt Engineering
PaperAPO Tool
PublicationJournal2025
The Role of Large Language Model-Generated Stories in the Narrative Experience of Serious Visual Novel Games
Mustafa Can GursesliSiyuan Chen
Venue
Published in International Journal of Human–Computer Interaction.
Large Language Models
Prompt Engineering
Paper
PublicationConference2025
Typhoon T1: An Open Thai Reasoning Model
Pittawat TaveekitworachaiPotsawee Manakul
Venue
Published in International Conference on Learning Representations (ICLR) - Open Science for Foundation Models (SCI-FM) 2025 Workshop.
Large Language Models
Reasoning Models
Supervised Fine-Tuning
PaperTyphoon T1 (Research Preview)
PublicationJournal2024
A Systematic Review of Major Evaluation Metrics for Simulator-Based Automatic Assessment of Driving after Stroke
Pittawat TaveekitworachaiGunt Chanmas
Venue
Published in Heliyon Vol. 10, Issue 12, E32930.
Simulator-based Driving Assessment
Post-Stroke Driving
Paper
PublicationConference2024
Assessing Inherent Biases Following Prompt Compression of Large Language Models for Game Story Generation
Pittawat TaveekitworachaiKantinan PlupattanakitRuck Thawonmas
Venue
Published in IEEE Conference on Games (CoG) 2024.
Large Language Models
Prompt Engineering
PaperResearch artifacts
PublicationConference2024
ChatGPT4PCG 2 Competition: Prompt Engineering for Science Birds Level Generation
Pittawat TaveekitworachaiFebri Abdullah
Venue
Published in IEEE Conference on Games (CoG) 2024.
Large Language Models
Prompt Engineering
PaperResearch artifacts
PublicationConference2024
Don't Do That! Reverse Role Prompting Helps Large Language Models Stay in Personality Traits
Siyuan ChenPittawat Taveekitworachai
Venue
Published in International Conference on Interactive Digital Storytelling (ICIDS) 2024.
Role Prompting
Reverse Role Prompting
Paper
PublicationJournal2024
Driving Assistant Using Generative AI Pre-generated Messages in Simulator-Based Driving Assessment: A Step Towards Low-Cost Simulator-Based Driving Assessment
Gunt ChanmasPittawat Taveekitworachai
Venue
Published in Heliyon Vol. 10, Issue 16, E35941.
Simulator-based Driving Assessment
Post-Stroke Driving
Paper
PublicationConference2024
Dungeons, Dragons, and Emotions: A Preliminary Study of Player Sentiment in LLM-driven TTRPGs
Xiao YouPittawat Taveekitworachai
Venue
Published in ACM International Conference on the Foundations of Digital Games (FDG) 2024.
Large Language Models
LLM-Powered Games
Paper
PublicationConference2024
LLMs in Eduverse: LLM-Integrated English Educational Game in Metaverse
Kantinan PlupattanakitPratch Suntichaikul
Venue
Published in IEEE Global Conference on Consumer Electronics (GCCE) 2024.
Large Language Models
Prompt Engineering
Paper
PublicationPreprint2024
Multiverse of Greatness: Generating Story Branches with LLMs
Pittawat TaveekitworachaiChollakorn Nimpattanavong
Venue
Published in arXiv.
Large Language Models
Low-resource LLMs
PaperResearch artifacts
PublicationConference2024
Null-Shot Prompting: Rethinking Prompting Large Language Models With Hallucination
Pittawat TaveekitworachaiFebri AbdullahRuck Thawonmas
Venue
Published in The Conference on Empirical Methods in Natural Language Processing (EMNLP) 2024, Main.
Null-Shot Prompting
Hallucination
Paper
PublicationConference2024
Prompt Evolution Through Examples for Large Language Models—A Case Study in Game Comment Toxicity Classification
Pittawat TaveekitworachaiFebri Abdullah
Venue
Published in IEEE International Workshop on Metrology for Industry 4.0 & IoT 2024.
Large Language Models
Prompt Engineering
PaperResearch artifacts
PublicationConference2024
Speed Up! Cost-Effective Large Language Model for ADAS Via Knowledge Distillation
Pittawat TaveekitworachaiPratch Suntichaikul
Venue
Published in IEEE Intelligent Vehicles Symposium (IV 2024) (Nominated for Best Paper).
Large Language Models
Knowledge Distillation
PaperResearch artifacts
PublicationConference2024
Temporal Collage Prompting: A Cost-Effective Simulator-Based Driving Accident Video Recognition With GPT-4o
Pratch SuntichaikulPittawat Taveekitworachai
Venue
Published in 8th International Conference on Information Technology (Best Paper Award).
Temporal Collage Prompting
Large Multimodal Models
Simulator-Based Driving Accident Video Recognition
Paper
PublicationJournal2024
The 1st ChatGPT4PCG Competition
Febri AbdullahPittawat Taveekitworachai
Venue
Published in IEEE Transactions on Games.
Large Language Models
Prompt Engineering
Paper
PublicationConference2024
Towards LLM4PCG: A Preliminary Evaluation of Open-Weight Large Language Models Beyond ChatGPT4PCG
Pittawat TaveekitworachaiYi Xia
Venue
Published in IEEE Conference on Games (CoG) 2024.
Large Language Models
Prompt Engineering
Paper
PublicationPreprint2024
Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
Kunat PipatanakulPotsawee Manakul
Venue
Published in arXiv.
Large Language Models
Large Multimodal Models
Paper
PublicationConference2023
Am I Fighting Well? Fighting Game Commentary Generation With ChatGPT
Chollakorn NimpattanavongPittawat Taveekitworachai
Venue
Published in 13th International Conference on Advances in Information Technology (IAIT).
Large Language Models
LLM Evaluation
PaperResearch artifacts
PublicationConference2023
Analyzing Audience Comments: Improving Interactive Narrative with ChatGPT
Xiaoxu LiXiao You
Venue
Published in International Conference on Interactive Digital Storytelling (ICIDS) 2023.
Large Language Models
Audience Participation Games
Paper
PublicationConference2023
Breaking bad: Unraveling Influences and Risks of User Inputs to ChatGPT for Game Story Generation
Pittawat TaveekitworachaiFebri Abdullah
Venue
Published in International Conference on Interactive Digital Storytelling (ICIDS) 2023.
Large Language Models
Risks in LLMs
PaperResearch artifacts
PublicationConference2023
ChatGPT4PCG Competition: Character-like Level Generation for Science Birds
Pittawat TaveekitworachaiFebri Abdullah
Venue
Published in IEEE Conference on Games (CoG) 2023.
Large Language Models
Prompt Engineering
PaperResearch artifacts
PublicationJournal2023
Driving scenarios and environmental settings in simulator-based driving assessment systems for stroke: a systematic review
Gunt ChanmasPittawat Taveekitworachai
Venue
Published in Topics in Stroke Rehabilitation.
Systematic Review
Simulator-based Driving Assessment
Paper
PublicationConference2023
Enhancing Novelty in ChatGPT Responses: Incorporating Random Word Brainstorming
Pittawat TaveekitworachaiRuck Thawonmas
Venue
Published in 13th International Conference on Advances in Information Technology (IAIT).
Large Language Models
Prompt Engineering
PaperResearch artifacts
PublicationConference2023
Journey of ChatGPT from Prompts to Stories in Games: the Positive, the Negative, and the Neutral
Pittawat TaveekitworachaiMustafa Can Gursesli
Venue
Published in IEEE International Conference on Consumer Electronic (ICCE)-Berlin 2023.
Large Language Models
Biases in LLMs
PaperResearch artifacts
PublicationConference2023
The Chronicles of ChatGPT: Generating and Evaluating Visual Novel Narratives on Climate Change Through ChatGPT
Mustafa Can GursesliPittawat Taveekitworachai
Venue
Published in International Conference on Interactive Digital Storytelling (ICIDS) 2023.
Large Language Models
Prompt Engineering
PaperResearch artifacts
PublicationConference2023
What Is Waiting for Us at the End? Inherent Biases of Game Story Endings in Large Language Models
Pittawat TaveekitworachaiFebri Abdullah
Venue
Published in International Conference on Interactive Digital Storytelling (ICIDS) 2023.
Large Language Models
Biases in LLMs
Paper
PublicationConference2022
Krathu-500: Post-Comments Thai Corpus
Pittawat TaveekitworachaiJonathan H. Chan
Venue
Published in The Research, Invention, and Innovation Congress (RI2C) 2022.
Natural Language Processing Datasets
Thai
Sentiment Analysis
PaperResearch artifacts

Academic service

Reviewer and service roles across conferences and journals.

Conferences and workshops

Journals

IEEE Transactions on Games (ToG) Reviewer

2024 | 2025 | 2026