Papers by Hanyu Duan
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. |