← Search

Binwei Yao

3 accepted papers

2025

No Preference Left Behind: Group Distributional Preference Optimization

ICLR 2025poster

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the distributional pluralistic preferences within a group. These m…

2024

Benchmarking Machine Translation with Cultural Awareness

EMNLP 2024finding

Translating culture-related content is vital for effective cross-cultural communication. However, many culture-specific items (CSIs) often lack literal translation across languages, making it challenging to collect high-quality, diverse parallel corpora with CSI annotations. This difficulty hinders…

2022

D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat

EMNLP 2022main

In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria. Such a dialogue system is distinguished from existing single-purpose human-machine dialog systems,…