Papers by Zaiwen Feng

1 papers
Trustworthy and Explainable Causal Representation Learning in Transformers (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to interpretable representation learning rely on masks that weight the significance of input features, but the origin of these masks is uncertain.
Approach: They propose a causal framework that directly learns identifiable representations from attention weights rather than relying on importance masks.
Outcome: The proposed framework learns identifiable and explainable representations from attention weights, rather than masks, and guarantees faithfulness on real-world 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