Specific Works
T-COL
T-COL is a counterfactual explanation generation method. It utilizes a link tree structure to select several local feature subsets through a partitioning strategy, which are eventually stitched together into a counterfactual interpretation.
- URL: https://github.com/sci-m-wang/T-COL
- Paper: T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems
- Obligation: Person in Charge
MM-Bigbench
MM-BigBench, with a range of diverse metrics to thoroughly evaluate different models and instructions, including the Best Performance metric, the Mean Relative Gain metric, the Stability metric, and the Adaptability metric.
- URL: https://github.com/declare-lab/MM-BigBench
- Paper: MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks
- Obligation: Key Participant
PICA
Although traditional language models play a good role in giving help, there is a problem of emotional participation deficiency, since long suggestive replies are against the goal of empathy. To solve the problem, we put forward the multi-turn dialogue model PICA, a chatbot that can empathize and rely on the emotion required.
- URL: https://github.com/NEU-DataMining/PICA
- Obligation: Key Participant
Rocar
Rocking Car is a method for evaluating LLM’s multilevel reasoning ability on graphs using interpersonal relationships. It is named after a Chinese children’s toy.
- URL: https://github.com/NEU-DataMining/RoCar
- Paper: RoCar: A Relationship Network-based Evaluation Method to Large Language Models
- Obligation: Person in Charge
Research Projects
A Study of Interpretable Dialogue Generation Techniques for Emotion Awareness (No.62172086)
Student Participant; Funding: ¥600,000
National Natural Science Foundation of China (NSFC)
Internet of Things Teaching Experiment Box (No.201810217141)
Person in Charge; Funding: ¥10,000
National Student Innovation Training Projects
Smart Home System Based on Internet of Things (No.201810217140)
Key Participants; Funding: ¥15,000
National Student Innovation Training Projects
Adsorption Type Underwater Hull Surface Inspection Robot (No.201810217024)
Key Participants; Funding: ¥12,000
National Student Innovation Training Projects
Ant Travel (No.201810217256)
Key Participants; Funding: ¥27,000
National Student Entrepreneurship Training Projects
Indoor Space Optimisation and Beautification System Based on Deep Learning (No.Z-2018-039)
Person in Charge; Funding: ¥5,000
Harbin Engineering University Student Innovation Training Projects (Significant type)