Papers by Feifan Yi

2 papers
ATLANTIS: Weak-to-Strong Learning via Importance Sampling (2025.acl-long)

Copied to clipboard

Challenge: ATLANTIS is a new technique to improve the performance of large language models.
Approach: They propose a new technique to bridge the gap between the distribution of current datasets and the real-world data distribution by using importance sampling.
Outcome: The proposed technique can bring consistent and significant improvements to models’ performance and can be flexibly transferred among models with different structures.
An Instruction Tuning-Based Contrastive Learning Framework for Aspect Sentiment Quad Prediction with Implicit Aspects and Opinions (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for aspect-based sentiment analysis have not explored how to effectively leverage the knowledge of pre-trained language models to handle implicit aspects and opinions.
Approach: They propose a framework leveraging Instruction Tuning and Supervised Contrastive Learning to improve aspect sentiment quad prediction for implicit aspects and opinions.
Outcome: The proposed framework significantly outperforms existing methods on benchmark datasets.

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