Papers by Luping Shi

2 papers
Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages.
Approach: They propose to use large language models as a general-purpose interface across multiple tasks and languages.
Outcome: The proposed model performs better on 200K hours of 6-language data for voice generation applications.
RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration (2025.coling-main)

Copied to clipboard

Challenge: Empirical evaluations indicate that RAM2C-empowered LLMs excel in Chinese reading teaching, offering more personalized, and ethically safe teaching response.
Approach: They propose a framework to retrieve large language models into educational dialogues and organize them into multi-experts groups with distinct roles to generate the data.
Outcome: Empirical evaluations show that RAM2C-empowered LLMs excel in Chinese reading teaching, offering more personalized, and ethically safe teaching response.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations