Xin Mao

Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title

2019

Supplementing product information by extracting attribute values from title is a crucial task in e-Commerce domain. Previous studies treat each attribute only as an entity type and build one set of NER tags (e.g., BIO) …

Boosting the Speed of Entity Alignment 10 ×: Dual Attention Matching Network with Normalized Hard Sample Mining

2021

Seeking the equivalent entities among multi-source Knowledge Graphs (KGs) is the pivotal step to KGs integration, also known as entity alignment (EA). However, most existing EA methods are inefficient and poor in scalability. A recent …

Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration

2024 · arXiv (Cornell University)

While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associated with the Proximal Policy Optimization (PPO) algorithm, …

Efficient Process Reward Model Training via Active Learning

2025 · arXiv (Cornell University)

Process Reward Models (PRMs) provide step-level supervision to large language models (LLMs), but scaling up training data annotation remains challenging for both humans and LLMs. To address this limitation, we propose an active learning approach, …