Lei Sha
University of Oxford
H-index: 17
Europe-United Kingdom
Top articles of Lei Sha
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Harnessing the Plug-and-Play Controller by Prompting | arXiv preprint arXiv:2402.04160 | Hao Wang Lei Sha | 2024/2/6 |
A Stable ‚Fast ‚and Fully Automatic Learning Algorithm for Predictive Coding Networks | Cornelius Emde Thomas Lukasiewicz Tommaso Salvatori Lei Sha Yuhang Song | 2024 | |
Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation | arXiv preprint arXiv:2404.12879 | Guanhua Chen Wenhan Yu Lei Sha | 2024/4/19 |
Text Attribute Control via Closed-Loop Disentanglement | Transactions of the Association for Computational Linguistics | Lei Sha Thomas Lukasiewicz | 2024/3/1 |
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors | arXiv preprint arXiv:2402.16444 | Zhexin Zhang Yida Lu Jingyuan Ma Di Zhang Rui Li | 2024/2/26 |
From Noise to Clarity: Unraveling the Adversarial Suffix of Large Language Model Attacks via Translation of Text Embeddings | arXiv preprint arXiv:2402.16006 | Hao Wang Hao Li Minlie Huang Lei Sha | 2024/2/25 |
Correcting Flaws in Common Disentanglement Metrics | arXiv preprint arXiv:2304.02335 | Louis Mahon Lei Shah Thomas Lukasiewicz | 2023/4/5 |
Rationalizing predictions by adversarial information calibration | Artificial Intelligence | Lei Sha Oana-Maria Camburu Thomas Lukasiewicz | 2023/2/1 |
Can you Trust your Disentanglement? | Louis Mahon Lei Sha Thomas Lukasiewicz | 2022/9/29 | |
Incremental predictive coding: A parallel and fully automatic learning algorithm | arXiv preprint arXiv:2212.00720 | Tommaso Salvatori Yuhang Song Beren Millidge Zhenghua Xu Lei Sha | 2022/11/16 |
Bird-Eye Transformers for Text Generation Models | arXiv preprint arXiv:2210.03985 | Lei Sha Yuhang Song Yordan Yordanov Tommaso Salvatori Thomas Lukasiewicz | 2022/10/8 |
RecInDial: A unified framework for conversational recommendation with pretrained language models | arXiv preprint arXiv:2110.07477 | Lingzhi Wang Huang Hu Lei Sha Can Xu Kam-Fai Wong | 2021/10/14 |
Finetuning large-scale pre-trained language models for conversational recommendation with knowledge graph | arXiv preprint arXiv:2110.07477 | Lingzhi Wang Huang Hu Lei Sha Can Xu Kam-Fai Wong | 2021 |
Unifying Categorical Models by Explicit Disentanglement of the Labels' Generative Factors | Luca Pinchetti Lei Sha Thomas Lukasiewicz | 2021/10/6 | |
Associative memories via predictive coding | Advances in Neural Information Processing Systems | Tommaso Salvatori Yuhang Song Yujian Hong Lei Sha Simon Frieder | 2021/12/6 |
Controlling text edition by changing answers of specific questions | arXiv preprint arXiv:2105.11018 | Lei Sha Patrick Hohenecker Thomas Lukasiewicz | 2021/5/23 |
Small changes make big differences: Improving multi-turn response selection in dialogue systems via fine-grained contrastive learning | arXiv preprint arXiv:2111.10154 | Yuntao Li Can Xu Huang Hu Lei Sha Yan Zhang | 2021/11/19 |
Multi-type Disentanglement without Adversarial Training | Proceedings of the 35th AAAI Conference on Artificial Intelligence‚ AAAI 2021‚ Virtual Conference‚ February 2–9‚ 2021 | Lei Sha Thomas Lukasiewicz | 2021/2 |
Learning from the Best: Rationalizing Predictions by Adversarial Information Calibration | Proceedings of the 35th AAAI Conference on Artificial Intelligence‚ AAAI 2021‚ Virtual Conference‚ February 2–9‚ 2021 | Lei Sha Oana-Maria Camburu Thomas Lukasiewicz | 2021/2 |
Rationale production to support clinical decision-making | arXiv preprint arXiv:2111.07611 | Niall Taylor Lei Sha Dan W Joyce Thomas Lukasiewicz Alejo Nevado-Holgado | 2021/11/15 |