Xuanli He
29 papers · 2018–2025 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🗺️ Taxonomy Completionist (49) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🧬
Topic Evolution
🤝
Dynamic Duo
(13)
👥
Mega-Team · Legion
❓
The Questioner
(2)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(142)
Top co-authors
Research topics
Machine Learning
(23)
Natural Language Processing
(22)
Artificial Intelligence
(21)
Core AI
(20)
Application Areas
(16)
Deep Learning
(11)
Applications
(11)
Resources & Methods
(11)
Learning Types · Machine Learning
(9)
Learning Types · Deep Learning
(8)
Optimization & Theory
(4)
Security & Privacy
(3)
Architectures
(3)
Generation
(2)
Privacy
(2)
Keywords
backdoor attack
(7)
neural machine translation
(5)
large language model
(4)
model extraction
(4)
natural language processing
(4)
domain adaptation
(3)
api security
(3)
adversarial attack
(3)
imitation attack
(3)
trigger detection
(2)
low-resource language
(2)
machine translation
(2)
model merging
(2)
question answering
(2)
text generation
(2)
intellectual property
(2)
adversarial learning
(2)
information retrieval
(2)
language model
(2)
nlp security
(2)
Papers
An Auditing Test to Detect Behavioral Shift in Language Models
ICLR 2025
Are We Done with MMLU?
NAACL 2025
Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
EMNLP 2025
GRADA: Graph-based Reranking against Adversarial Documents Attack
EMNLP 2025
IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models
NAACL 2025
Self-Training Large Language Models for Tool-Use Without Demonstrations
NAACL 2025
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
NAACL 2025
TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
ACL 2025
AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages
NAACL 2024
Backdoor Attacks on Multilingual Machine Translation
NAACL 2024
Here’s a Free Lunch: Sanitizing Backdoored Models with Model Merge
ACL 2024
Using Natural Language Explanations to Improve Robustness of In-context Learning
ACL 2024
IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks
ACL 2023
Koala: An Index for Quantifying Overlaps with Pre-training Corpora
EMNLP 2023
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation
EMNLP 2023
Rethinking Round-Trip Translation for Machine Translation Evaluation
ACL 2023
Security Challenges in Natural Language Processing Models
EMNLP 2023
Can Domains Be Transferred across Languages in Multi-Domain Multilingual Neural Machine Translation?
EMNLP 2022
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks
NeurIPS 2022
Extracted BERT Model Leaks More Information than You Think!
EMNLP 2022
Foiling Training-Time Attacks on Neural Machine Translation Systems
EMNLP 2022
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
AAAI 2022
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs
COLING 2022
Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection
EMNLP 2021
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!
NAACL 2021
Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness
EMNLP 2020
Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
ACL 2020
Scene Graph Modification Based on Natural Language Commands
EMNLP 2020
Sequence to Sequence Mixture Model for Diverse Machine Translation
CoNLL 2018