Han Zhou

PhD student in NLP

Biography

I am a third-year PhD student in Computation, Cognition, and Language (NLP) at Language Technology Lab, University of Cambridge. I am supervised by Prof. Anna Korhonen and Dr. Ivan Vulić. I am also a Student Researcher at Google Cloud AI Research. Previously, I interned at the Gemini Responsible AI Team at Google Research.

I am always interested in modular, efficient, and reward-driven intelligence.

Recent News

Sep 2024: ZEPO and TopViewRS were accepted at EMNLP 2024!
Jul 2024: Start as Student Researcher at Google Cloud AI Research.
Jul 2024: PairS was accepted at COLM 2024!
May 2024: Attended ICLR 2024 in-person 🇦🇹.
Jan 2024: AutoPEFT was accepted at TACL 2024!
Jan 2024: Batch Calibration is accepted to ICLR 2024! Batch Calibration has been featured in Google AI blog and presented as a spotlight at NeurIPS 2023 R0-FoMo.

Academic Services

Reviewer/program committee member at ACL (2023-24), EMNLP (2022-24), ICML (2024), NeurIPS (2023-24), ICLR (2025).

Interests

Large Language Models
Parameter-Efficient Fine-Tuning
Prompt Optimization
Modularity

Education

PhD in Computation, Cognition, and Language, Oct 2022 -

University of Cambridge
MSc in Machine Learning (rank 1st), 2020 - 2021

University College London
BA, MEng in Engineering Science, 2015 - 2019

University of Oxford

Featured Publications

Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy

January, 2024 International Conference on Learning Representations (ICLR)

Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering

Mitigating prompt biases and unifying existing calibration approaches without labeled data.

Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen

January, 2024 Transactions of the Association for Computational Linguistics (TACL)

AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning

Automatic discovery of families of high-performing PEFT configurations.

Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen

October, 2023 Findings of the Association for Computational Linguistics (EMNLP)

Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning

Efficient prompt optimization via influential search space pruning.

Publications

Quickly discover relevant content by filtering publications.

Han Zhou, Xingchen Wan, Yinhong Liu, Nigel Collier, Ivan Vulić, Anna Korhonen (2024). Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF Cite Code Abstract ACL Anthology

Chengzu Li, Caiqi Zhang, Han Zhou, Nigel Collier, Anna Korhonen, Ivan Vulić (2024). TopViewRS: Vision-Language Models as Top-View Spatial Reasoners. The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF Cite Code Abstract Project Page ACL Anthology

Yinhong Liu, Han Zhou, Zhijiang Guo, Ehsan Shareghi, Ivan Vulić, Anna Korhonen, Nigel Collier (2024). Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators. The First Conference on Language Modeling (COLM).

PDF Cite Code Abstract OpenReview

Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy (2024). Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering. International Conference on Learning Representations (ICLR).

PDF Cite Abstract (Google Research) OpenReview Blog (Google AI) Talk (NeurIPS Spotlight)

Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen (2024). AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning. Transactions of the Association for Computational Linguistics (TACL).

PDF Cite Code Abstract MIT Press ACL Anthology

Chengzu Li, Han Zhou, Goran Glavaš, Anna Korhonen, Ivan Vulić (2023). Can Large Language Models Achieve Calibration with In-Context Learning?. ICLR 2024 Workshop on Reliable and Responsible Foundation Models.

PDF Cite Code Abstract OpenReview

Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen (2023). Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning. Findings of the Association for Computational Linguistics (EMNLP).

PDF Cite Code Abstract OpenReview ACL Anthology

Songbo Hu, Han Zhou, Zhangdie Yuan, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Anna Korhonen, Ivan Vulić (2023). A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems. The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF Cite Code Abstract OpenReview ACL Anthology

Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen (2023). Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems. Transactions of the Association for Computational Linguistics (TACL).

PDF Cite Dataset Abstract MIT Press ACL Anthology

Qingcheng Zeng, Lucas Garay, Peilin Zhou, Dading Chong, Yining Hua, Jiageng Wu, Yikang Pan, Han Zhou, Rob Voigt, Jie Yang (2023). GreenPLM: Cross-Lingual Transfer of Monolingual Large Language Models at Almost No Cost. The 32nd International Joint Conference on Artificial Intelligence (IJCAI).

PDF Cite Code Abstract IJCAI 2023

Han Zhou, Ignacio Iacobacci, Pasquale Minervini (2023). XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking. Findings of the Association for Computational Linguistics (EACL).

PDF Cite Code Abstract ACL Anthology