Processing and Acquisition of Language in Machines and Mind (PALM) Group 
Welcome to PALM Group at MBZUAI!
We explore the intersection among natural language processing (NLP), linguistics, and computational cognitive modeling.
We purse the questions, for example:
- How can NLP contribute to fundamental research of language and humans (particularly on cognitive modeling topics)?
- How can NLP benefit from language science?
- How can we approach to understanding language and reasoning in artificial intelligence? (interpretability topics)
- How and why are language processing and acquisition similar/different between artificial intelligence and humans?
The PALM Group commenced in Fall 2025 (led by Tatsuki Kuribayashi) and belongs to MBZUAI NLP department.
For future members:
If you are interested in MSc/PhD opportunities for 2026 admission, you should directly apply via MBZUAI admission page (2025 deadline: December 15th), and specify Tatsuki as a preferred supervisor (in, e.g., Research Statement). Please also check this page for prospective students. We do not currently accept internship.
News
Jul. 2026
5 papers involving our members have been accepted:
- Ryo Yoshida, Shinnosuke Isono, Taiga Someya, Yohei Oseki, Tatsuki Kuribayashi.
"An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal." (main conf.) - Ruoxi Ning, Yongpeng Zhu, Qingcheng Zeng, Tatsuki Kuribayashi, Freda Shi.
"On the Effect of Hyperparameters in Language Modeling for Computational Linguistics." (main conf.) - Tatsuki Kuribayashi, Alex Warstadt, Yohei Oseki, Ethan Gotlieb Wilcox.
"Dual Alignment Between Language Model Layers and Human Sentence Processing." (main conf.) - Saeed Almheiri, Bilal Elbouardi, Salsabila Zahirah Pranida, Irina Nikishina, Ashwath Rao B, Parameswari Krishnamurthy, Muhammad Cendekia Airlangga, Rifo Ahmad Genadi, Nguyễn Phan Gia Bảo, Amir Hossein Yari, Hawau Olamide Toyin, Nurdaulet Mukhituly, Mena Attia, Besher Hassan, Ahmad Fathan Hidayatullah, Tatsuki Kuribayashi, Haonan Li, Suma Bhat, Fajri Koto.
"Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages." (main conf.) - Junlin Li, David Robert Reich, Yu-yin Hsu.
"Lending Eyesight to Language Models: Modeling and Probing Human scanpath through Transformer Decoder." (Findings)
Jul. 2026
1 paper involving our member has been accepted:
- Alham Fikri Aji, Afifa Amriani, Rendi Chevi, Ayu Purwarianti, Derry Wijaya.
"AI Misconception and Adoption Among Indonesian K-12 Teachers."
May. 2026
1 paper involving our member has been accepted:
- Nadine El-Naggar, Tatsuki Kuribayashi, Ted Briscoe.
"What Kind of Language is Easy to Language-Model Under Curriculum Learning?"
Mar. 2026
1 paper involving our member has been accepted:
- Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi, Shusaku Sone, Masaya Taniguchi, Ana Brassard, Keisuke Sakaguchi, Kentaro Inui.
"LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics." (Findings)
Dec. 2025
1 oral presentation has been made in Computational Psycholinguistics Meeting 2025
- Tatsuki Kuribayashi, Yohei Oseki, Souhaib Ben Taieb, Kentaro Inui, Timothy Baldwin.
"Large Language Models Are Human-Like Internally."
Dec. 2025
1 paper involving our member has been accepted by NeurIPS
- Mengyu Ye, Jun Suzuki, Tatsuro Inaba, Tatsuki Kuribayashi.
"Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders."
EMNLP 2025
Nov. 2025
1 EMNLP main paper involving our member has been accepted by EMNLP 2025.
- Nadine El-Naggar, Tatsuki Kuribayashi, Ted Briscoe.
"Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages." (main conf.)
- Tatsuki Kuribayashi, Yohei Oseki, Souhaib Ben Taieb, Kentaro Inui, Timothy Baldwin.
"Large Language Models Are Human-Like Internally."
TACL
Oct. 2025
1 paper involving our member has been accepted:
- Tianyang Xu, Tatsuki Kuribayashi, Yohei Oseki, Ryan Cotterell, Alex Warstadt.
"Can Language Models Learn Typologically Implausible Languages?"