Følg
Zhengyan Shi
Zhengyan Shi
Andre navnZhengxiang Shi
PhD Student at University College London
Verifisert e-postadresse på ucl.ac.uk - Startside
Tittel
Sitert av
Sitert av
År
StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts
Z Shi, Q Zhang, A Lipani
AAAI Conference on Artificial Intelligence (AAAI 2022) Oral Presentation, 2022
642022
Learning to Execute Actions or Ask Clarification Questions
Z Shi, Y Feng, A Lipani
Findings of the Association for Computational Linguistics: NAACL 2022, 2022
452022
DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
Z Shi, A Lipani
International Conference on Learning Representations (ICLR 2024), 2024
352024
Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner
Z Shi, A Lipani
Neural Information Processing Systems (NeurIPS 2023) Main Track, 2023
252023
Rethinking Semi-supervised Learning with Language Models
Z Shi, F Tonolini, N Aletras, E Yilmaz, G Kazai, Y Jiao
Findings of the Association for Computational Linguistics: ACL 2023, 2023
192023
Bayesian reward models for LLM alignment
AX Yang, M Robeyns, T Coste, Z Shi, J Wang, H Bou-Ammar, L Aitchison
Workshop on Secure and Trustworthy Large Language Models (ICLR 2024), 2024
142024
Instruction Tuning With Loss Over Instructions
Z Shi, AX Yang, B Wu, L Aitchison, E Yilmaz, A Lipani
Neural Information Processing Systems (NeurIPS 2024), 2024
122024
When and What to Ask Through World States and Text Instructions
Z Shi, J Ramos, TE Kim, X Wang, HA Rahmani, A Lipani
Neural Information Processing Systems (NeurIPS) IGLU Workshop 2022, 2023
9*2023
Investigating the potential of crowdsourced street-level imagery in understanding the spatiotemporal dynamics of cities: A case study of walkability in Inner London
M Wang, J Haworth, H Chen, Y Liu, Z Shi
Cities 153, 105243, 2024
72024
Self Contrastive Learning For Session-based Recommendation
Z Shi, X Wang, A Lipani
European Conference on Information Retrieval (ECIR 2024) Full Paper, 2023
62023
Understanding the Role of User Profile in the Personalization of Large Language Models
B Wu, Z Shi, HA Rahmani, V Ramineni, E Yilmaz
arXiv preprint arXiv:2406.17803, 2024
42024
Lexical Entrainment for Conversational Systems
Z Shi, P Sen, A Lipani
Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
42023
Rethink the Effectiveness of Text Data Augmentation: An Empirical Analysis
Z Shi, A Lipani
European Symposium on Artificial Neural Networks: ESANN 2023, 2023
42023
Attention-based ingredient phrase parser
Z Shi, P Ni, M Wang, TE Kim, A Lipani
European Symposium on Artificial Neural Networks: ESANN 2022, 2022
42022
Condita: A State Machine Like Architecture for Multi-Modal Task Bots
J Ramos, TE Kim, Z Shi, X Fu, F Ye, Y Feng, A Lipani
Amazon Alexa Prize TaskBot Challenge Proceedings, 2022
32022
Understanding likelihood over-optimisation in direct alignment algorithms
Z Shi, S Land, A Locatelli, M Geist, M Bartolo
arXiv preprint arXiv:2410.11677, 2024
12024
SummEQuAL: Summarization Evaluation via Question Answering using Large Language Models
J Liu, Z Shi, A Lipani
Proceedings of the 2nd Workshop on Natural Language Reasoning and Structured …, 2024
12024
When Can Proxies Improve the Sample Complexity of Preference Learning?
Y Zhu, DA de Souza, Z Shi, M Yang, P Minervini, A D'Amour, MJ Kusner
arXiv preprint arXiv:2412.16475, 2024
2024
Understanding Users’ Confidence in Spoken Queries for Conversational Search Systems
Y Yu, Z Shi, A Lipani
International Conference on Engineering Applications of Neural Networks, 405-418, 2024
2024
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–19