Papers by Hanyu Duan

4 papers
BARLE: Background-Aware Representation Learning for Background Shift Out-of-Distribution Detection (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for OOD detection focus on identifying semantic-shift OOD samples . background-shift detection is more practical but challenging .
Approach: They propose a background-aware representation learning approach for background-shift OOD detection in NLP.
Outcome: The proposed method improves background-shift OOD detection while maintaining ID classification accuracy.
Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models (2026.findings-eacl)

Copied to clipboard

Challenge: Text embedding models are widely used in natural language processing but are often benchmarked on tasks that do not require understanding nuanced numerical information in text.
Approach: They evaluate 13 widely used text embedding models and find they struggle to capture numerical details accurately.
Outcome: The proposed models struggle to capture nuanced numerical details accurately, despite being benchmarked on tasks that do not require understanding nuance.
Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing models for numeracy-intensive applications fail to learn numerability . existing models fail to handle numbers, resulting in performance problems .
Approach: They propose a number embedding approach that embeds numbers into dimensional space . they construct a knowledge graph consisting of number entities and magnitude relations .
Outcome: The proposed method is easy to implement and shows that it performs well on numeracy-related tasks.
Exploring the Relationship between In-Context Learning and Instruction Tuning (2024.findings-emnlp)

Copied to clipboard

Challenge: In-Context Learning (ICL) and Instruction Tuning (IT) are two primary paradigms of adopting Large Language Models (LLMs) to downstream applications, but they are significantly different.
Approach: They examine how the hidden states of Large Language Models change in these two paradigms by examining how they differ in implementation.
Outcome: The proposed model changes the hidden states of LLMs as if its accompanying demonstrations were used to instructionally tune the model.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations