Haozhe An
8 papers · 2020–2025 · 4 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 🐣 Hot Topic Early Bird
❓
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(7)
Machine Learning
(6)
Application Areas
(6)
Core AI
(6)
Natural Language Processing
(3)
Deep Learning
(2)
Applications
(2)
Architectures
(1)
Core Methods
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Learning Types · Machine Learning
(1)
Resources & Methods
(1)
Keywords
large language model
(4)
gender bia
(3)
bias detection
(3)
social bia
(2)
commonsense knowledge
(1)
language model evaluation
(1)
model behavior
(1)
convolutional neural network
(1)
language model
(1)
evaluation benchmark
(1)
cultural bia
(1)
commonsense reasoning
(1)
algorithmic bia
(1)
word embedding
(1)
multilingual evaluation
(1)
relationship prediction
(1)
racial bia
(1)
demographic bia
(1)
representation analysis
(1)
embedding analysis
(1)
Papers
On the Mutual Influence of Gender and Occupation in LLM Representations
ACL 2025
Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?
ACL 2024
On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models
EMNLP 2024
Susu Box or Piggy Bank: Assessing Cultural Commonsense Knowledge between Ghana and the US
EMNLP 2024
Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biases
ACL 2023
SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models
EACL 2023
Learning Bias-reduced Word Embeddings Using Dictionary Definitions
ACL 2022
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
ICML 2020