Papers by Harsh Pal

1 papers
Uncovering Currency Bias and Syntax Gap in Text Embedding Models (2026.findings-acl)

Copied to clipboard

Challenge: Text-embedding models often inherit societal biases, yet the influence of socio-economic markers remains unexplored.
Approach: They propose to identify Currency Bias as a systemic representational limitation in financial AI . they analyze currency embeddings to identify currency identifiers and associative sensitivity .
Outcome: The proposed model lacks associative sensitivity to economic hierarchies, the authors show . they show that current embedding practices pose significant risks for the fairness and reliability of financial NLP applications.

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