Xuanli He

Xuanli He

Monash University

H-index: 14

Oceania-Australia

Contact Xuanli He

About Xuanli He

Xuanli He, With an exceptional h-index of 14 and a recent h-index of 14 (since 2020), a distinguished researcher at Monash University, specializes in the field of Natural Language Processing, Machine Learning.

His recent articles reflect a diverse array of research interests and contributions to the field:

Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning

Attacks on Third-Party APIs of Large Language Models

The Hallucinations Leaderboard--An Open Effort to Measure Hallucinations in Large Language Models

Backdoor Attack on Multilingual Machine Translation

StarCoder 2 and The Stack v2: The Next Generation

Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge

Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation

Security challenges in natural language processing models

Xuanli He Information

University	Monash University
Position	___
Citations(all)	814
Citations(since 2020)	773
Cited By	210
hIndex(all)	14
hIndex(since 2020)	14
i10Index(all)	16
i10Index(since 2020)	16
Email	Access Email
University Profile Page	Monash University
Google Scholar	View Google Scholar Profile

Xuanli He Skills & Research Interests

Natural Language Processing

Machine Learning

Top articles of Xuanli He

Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning

arXiv preprint arXiv:2404.19597

2024/4/30

Xuanli He

H-Index: 7

Jun Wang

H-Index: 10

Qiongkai Xu

H-Index: 8

Pasquale Minervini

H-Index: 12

Attacks on Third-Party APIs of Large Language Models

arXiv preprint arXiv:2404.16891

2024/4/24

Xuanli He

H-Index: 7

Qiongkai Xu

H-Index: 8

The Hallucinations Leaderboard--An Open Effort to Measure Hallucinations in Large Language Models

arXiv preprint arXiv:2404.05904

2024/4/8

Xiaotang Du

H-Index: 3

Yu Zhao

H-Index: 0

Xuanli He

H-Index: 7

Pasquale Minervini

H-Index: 12

Backdoor Attack on Multilingual Machine Translation

arXiv preprint arXiv:2404.02393

2024/4/3

Jun Wang

H-Index: 10

Qiongkai Xu

H-Index: 8

Xuanli He

H-Index: 7

Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge

arXiv preprint arXiv:2402.19334

2024/2/29

Xuanli He

H-Index: 7

Maximilian Mozes

H-Index: 5

Mark Dras

H-Index: 21

Qiongkai Xu

H-Index: 8

Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation

arXiv preprint arXiv:2402.16889

2024/2/23

Xuanli He

H-Index: 7

Qiongkai Xu

H-Index: 8

Wei Lu

H-Index: 21

Security challenges in natural language processing models

2023/12

Qiongkai Xu

H-Index: 8

Xuanli He

H-Index: 7

AfriMTE and AfriCOMET: Empowering COMET to Embrace Under-resourced African Languages

arXiv preprint arXiv:2311.09828

2023/11/16

Jiayi Wang

H-Index: 1

David Ifeoluwa Adelani

H-Index: 6

Sweta Agrawal

H-Index: 3

Eleftheria Briakou

H-Index: 3

Marine Carpuat

H-Index: 20

Xuanli He

H-Index: 7

Samuel Njoroge

H-Index: 8

Using Natural Language Explanations to Improve Robustness of In-context Learning for Natural Language Inference

arXiv preprint arXiv:2311.07556

2023/11/13

Xuanli He

H-Index: 7

Yuxiang Wu

H-Index: 3

Oana-Maria Camburu

H-Index: 7

Pasquale Minervini

H-Index: 12

Can Knowledge Graphs Simplify Text?

2023/10/21

Xuanli He

H-Index: 7

Yang Bai

H-Index: 11

Daisy Zhe Wang

H-Index: 15

Use of llms for illicit purposes: Threats, prevention measures, and vulnerabilities

arXiv preprint arXiv:2308.12833

2023/8/24

Maximilian Mozes

H-Index: 5

Xuanli He

H-Index: 7

Lewis D Griffin

H-Index: 23

IMBERT: Making BERT immune to insertion-based backdoor attacks

arXiv preprint arXiv:2305.16503

2023/5/25

Xuanli He

H-Index: 7

Jun Wang

H-Index: 10

G3detector: General gpt-generated text detector

arXiv preprint arXiv:2305.12680

2023/5/22

Xuanli He

H-Index: 7

Qiongkai Xu

H-Index: 8

Yuxiang Wu

H-Index: 3

Mitigating backdoor poisoning attacks through the lens of spurious correlation

EMNLP

2023/5/19

Xuanli He

H-Index: 7

Qiongkai Xu

H-Index: 8

Jun Wang

H-Index: 10

Koala: An index for quantifying overlaps with pre-training corpora

2023/3/26

Thuy-Trang Vu

H-Index: 3

Xuanli He

H-Index: 7

Overview of the 2023 ALTA Shared Task: Discriminate between Human-Written and Machine-Generated Text

ALTA

2023

Diego Molla

H-Index: 12

Xuanli He

H-Index: 7

Qiongkai Xu

H-Index: 8

Cater: Intellectual property protection on text generation apis via conditional watermarks

NeurIPS

2022/9/19

Xuanli He

H-Index: 7

Qiongkai Xu

H-Index: 8

Yi Zeng

H-Index: 5

Jiwei Li

H-Index: 32

Ruoxi Jia

H-Index: 16

Foiling Training-Time Attacks on Neural Machine Translation Systems

2022/12

Jun Wang

H-Index: 10

Xuanli He

H-Index: 7

Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?

arXiv preprint arXiv:2210.11628

2022/10/20

Thuy-Trang Vu

H-Index: 3

Xuanli He

H-Index: 7

Dinh Phung

H-Index: 32

See List of Professors in Xuanli He University(Monash University)

Co-Authors

H-index: 41

Gholamreza (Reza) Haffari — Gholamreza (Reza) Haffari
Monash University

Visit Gholamreza (Reza) Haffari Page

H-index: 13

Qiongkai Xu — Qiongkai Xu
Australian National University

Visit Qiongkai Xu Page

1

academic-engine

Useful Links

List of top 50 universities

List of top 100 universities

List of top 500 universities

Find Professors Email

Find Universities Email

CUFinder Academic Engine