About Me

Hello! I am currently working on the Typhoon project, supported by the venture capital firm SCB 10X, which aims to develop large language models and speech technology for the Thai language.

I completed my PhD in NLP from the University of Cambridge, supervised by Prof. Mark Gales, with a research focus on summarization and NLP evaluation. I publish mostly in NLP conferences (ACL, EMNLP, *ACL) and speech conferences (Interspeech, ICASSP).

Previously, I worked as an applied scientist intern at Amazon. I hold a B.A. and an M.Eng. in Information and Computer Engineering from the University of Cambridge, obtained in 2019.

News

• 10/2024 [Preprint] SkillAggregation: Reference-free LLM-Dependent Aggregation
• 09/2024 [Conference] EMNLP 2024: 2*main + 1*findings as a co-author
• 09/2024 [Leaderboard] We released the Thai LLM Leaderboard (w/ VISTEC)
• 09/2024 [Leaderboard] We released ThaiExam in HELM (w/ Stanford CRFM)
• 08/2024 [Talk] Speak at AI CoP Seminar @ the U.S. SEC on LLM Hallucination
• 08/2024 [Talk] Speak at 3rd SEA Language Summit on Multimodal LLM
• 08/2024 [Model] We released Typhoon Multimodal: Audio Model & Vision Model
• 07/2024 [Talk] Speak at the Stock Exchange of Thailand (SET) on Thai LLM

Selected Publications

A complete list of publications is available on Google Scholar

• LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models
  Adian Liusie, Potsawee Manakul, Mark Gales
  EACL 2024 (main) [code]
• SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
  Potsawee Manakul, Adian Liusie, Mark Gales
  EMNLP 2023 (main) [project page]
  → Interview with the Washington Post about AI Hallucination in May 2023
  → Talk at ML Collective - Deep Learning: Classics and Trends (DLCT) in August 2023
  → An analysis by Daniel Huynh (from Mithril Security) on SelfCheckGPT
  → SelfCheckGPT featured in Stanford CS 329T: Trustworthy Machine Learning (Fall 2023)
  → SelfCheckGPT featured in deeplearning.ai short course
• MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization
  Potsawee Manakul, Adian Liusie, Mark Gales
  AACL 2023 (main) [code]
  → Area Chair Paper Award (Generation and Summarization)
• CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models
  Potsawee Manakul, Yassir Fathullah, Adian Liusie, Vyas Raina, Vatsal Raina, Mark Gales
  BioNLP Workshop @ ACL 2023 [code]
  → Best-performing system on the Problem List Summarization shared task
• Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems
  Potsawee Manakul, Mark Gales
  EMNLP 2021 (main) [code]
• Long-Span Summarization via Local Attention and Content Selection
  Potsawee Manakul, Mark Gales
  ACL 2021 (main) [code]
• CUED_SPEECH at TREC 2020 Podcast Summarisation Track
  Potsawee Manakul, Mark Gales
  TREC 2020 [code]
  → Won 1st place in the Spotify Podcast Summarisation task 2020
• Abstractive Spoken Document Summarization using Hierarchical Model with Multi-stage Attention Diversity Optimization
  Potsawee Manakul, Mark J. F. Gales, Linlin Wang
  Interspeech 2020 [code]
  → Best Student Paper Award Finalist
  
• Impact of ASR Performance on Spoken Grammatical Error Detection
  Yiting Lu, Mark J. F. Gales, Katherine M. Knill, Potsawee Manakul, Linlin Wang, Yu Wang
  Interspeech 2019
  
• Automatic grammatical error detection of non-native spoken learner English
  Katherine M. Knill, Mark J. F. Gales, Potsawee Manakul, Andrew P. Caines
  ICASSP 2019
  

Preprints

• SkillAggregation: Reference-free LLM-Dependent Aggregation
  Guangzhi Sun, Anmol Kagrecha, Potsawee Manakul, Phil Woodland, Mark Gales
  arXiv 2024
• Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models
  Potsawee Manakul, Guangzhi Sun, Warit Sirichotedumrong, Kasima Tharnpipitchai, Kunat Pipatanakul
  arXiv 2024 [demo]
• CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models
  Guangzhi Sun*, Potsawee Manakul*, Adian Liusie, Kunat Pipatanakul, Chao Zhang, Phil Woodland, Mark Gales
  arXiv 2024 *Equal contribution [multimodal hallucination leaderboard]

---

Reviewer Service

• ACL Rolling Review: 2024/02, 2024/04, 2024/06, 2024/10
• NeurIPS: 2023, 2024
• ICLR: 2024, 2025
• ICML: 2023, 2024
• AAAI: 2025
• Interspeech: 2023, 2024
• Conference On Language Modeling (COLM): 2024
• IEEE Transactions on Audio, Speech, and Language Processing: 2022, 2023, 2024

Honours and Awards

• AACL 2023 Area Chair Paper Award
• InterSpeech 2020 Best Student Paper Finalist
• Cambridge International & St John's College Scholarship (2019)
• BP 1st Year Prize (top 1% in 1st-year Cambridge Engineering, 2016)
• Silver Medalist at IPhO 2014; Gold Medalist at APhO 2014

Teaching @ Cambridge

• 3rd-year Undergraduate Supervision: 3F7 Information Theory and Coding
• 2nd-year Undergraduate Supervision: 2P7 Vector Calculus, Linear Algebra, Probability
• MPhil in Machine Learning & Machine Intelligence: Introduction to NLP (Lab demonstration)

---

Contact

• Email: m.potsawee-at-gmail.com

---