Publications
2026
- arXiv:2601.18129
Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models
K. Pipatanakul, P. TaveekitworachaiRead paper - arxiv:2509.20866
Single Answer is Not Enough: On Generating Ranked Lists with Medical Reasoning Models
P. Taveekitworachai, N. Pongjirapat, K. Chaisutyakorn, P. Ittichaiwong, T. Saengja, K. PipatanakulRead paper - arXiv:2601.14722
Typhoon OCR: Open Vision-Language Model For Thai Document Extraction
S. Nonesung, N. Nitarach, T. Jaknamon, P. Taveekitworachai, K. PipatanakulRead paper - arXiv:2601.13044
Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition
W. Sirichotedumrong, A. Na-Thalang, P. Manakul, P. Taveekitworachai, S. Sripaisarnmongkol, K. PipatanakulRead paper
2025
- EACL 2026 MAIN
Extending Audio Context for Long-Form Understanding in Large Audio-Language Models
Y. Chaichana, P. Taveekitworachai, W. Sirichotedumrong, P. Manakul, K. PipatanakulRead paper - Principled Design for Trustworthy AI Workshop @ ICLR 2026
ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts
T. Ukarapol, N. Chukamphaeng, K. Pipatanakul, P. SarapatRead paper - IJCNLP-AACL 2025 MAIN
ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai
S. Nonesung, T. Jaknamon, S. Chaiophat, N. Nitarach, C. Wittayasakpan, W. Sirichotedumrong, A. Na-Thalang, K. PipatanakulRead paper - WordPlay Workshop @ EMNLP 2025
Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
S. Ruangtanusak, P. Taveekitworachai, K. PipatanakulRead paper - arXiv:2507.14664
Mangosteen: An Open Thai Corpus for Language Model Pretraining
W. Phatthiyaphaibun, C. Udomcharoenchaikit, P. Singkorapoom, K. Pipatanakul, E. Chuangsuwanich, P. Limkonchotiwat, S. NutanongRead paper - EACL 2026 MAIN
AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation
P. Manakul, W. H. Gan, M. J. Ryan, A. S. Khan, W. Sirichotedumrong, K. Pipatanakul, W. Held, D. YangRead paper - FinNLP Workshop @ EMNLP 2025
FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning
N. Nitarach, W. Sirichotedumrong, P. Pitchayarthorn, P. Taveekitworachai, P. Manakul, K. PipatanakulRead paper - EMNLP 2025 MAIN
Prior Prompt Engineering for Reinforcement Fine-Tuning
P. Taveekitworachai, P. Manakul, S. Nutanong, K. PipatanakulRead paper - ACL 2025 Main
Mind the Gap! Static and Interactive Evaluations of Large Audio Models
M. Li, W. B. Held, M. J. Ryan, K. Pipatanakul, P. Manakul, H. Zhu, D. YangRead paper - arXiv:2502.12982
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLM
L. Dou, Q. Liu, F. Zhou, C. Chen, Z. Wang, Z. Jin, Z. Liu, T. Zhu, C. Du, P. Yang, H. Wang, J. Liu, Y. Zhao, X. Feng, X. Mao, M. T. Yeung, K. Pipatanakul, F. Koto, M. S. Thu, H. Kydlíček, Z. Liu, Q. Lin, S. Sripaisarnmongkol, K. Sae-Khow, N. Thongchim, T. Konkaew, N. Borijindargoon, A. Dao, M. Maneegard, P. Artkaew, Z.-X. Yong, Q. Nguyen, W. Phatthiyaphaibun, H. H. Tran, M. Zhang, S. Chen, T. Pang, C. Du, X. Wan, W. Lu, M. LinRead paper - SCI-FM Workshop @ ICLR 2025
Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
K. Pipatanakul, P. Taveekitworachai, P. Manakul, K. TharnpipitchaiRead paper - SCI-FM Workshop @ ICLR 2025
Typhoon T1: An Open Thai Reasoning Model
P. Taveekitworachai, P. Manakul, K. Tharnpipitchai, K. PipatanakulRead paper
2024
- arXiv:2412.13702
Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
K. Pipatanakul, P. Manakul, N. Nitarach, W. Sirichotedumrong, S. Nonesung, T. Jaknamon, P. Pengpun, P. Taveekitworachai, A. Na-Thalang, S. Sripaisarnmongkol, K. Jirayoot, K. TharnpipitchaiRead paper - Interspeech 2025 Main
Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models
P. Manakul, G. Sun, W. Sirichotedumrong, K. Tharnpipitchai, K. PipatanakulRead paper - RBFM Workshop @ NeurIPS 2024
CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models
G. Sun, P. Manakul, A. Liusie, K. Pipatanakul, C. Zhang, P. Woodland, et al.Read paper
2023