6 papers
A new approach for encoding code and assisting code understanding
Mengdan Fan, Wei Zhang, Haiyan Zhao +1
Some companies (e.g., Microsoft Research and Google DeepMind) have discovered some of the limitations of GPTs' autoregressive paradigm next-word prediction, manifested in the model…
Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment
Chengfeng Dou, Ying Zhang, Zhi Jin +4
This research examines the use of Reinforcement Learning from AI Feedback (RLAIF) techniques to improve healthcare dialogue models, with the aim of tackling the challenges of prefe…
GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
Wei Liu, Ailun Yu, Daoguang Zan +5
The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code…
Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback
Chengfeng Dou, Zhi Jin, Wenpin Jiao +3
The use of large language models in medical dialogue generation has garnered significant attention, with a focus on improving response quality and fluency. While previous studies h…
EVIT: Event-Oriented Instruction Tuning for Event Reasoning
Zhengwei Tao, Xiancai Chen, Zhi Jin +3
Events refer to specific occurrences, incidents, or happenings that take place under a particular background. Event reasoning aims to infer events according to certain relations an…
MEEL: Multi-Modal Event Evolution Learning
Zhengwei Tao, Zhi Jin, Junqiang Huang +5
Multi-modal Event Reasoning (MMER) endeavors to endow machines with the ability to comprehend intricate event relations across diverse data modalities. MMER is fundamental and unde…