Papers by Jennifer Dy

2 papers
QueryForm: A Simple Zero-shot Form Entity Query Framework (2023.findings-acl)

Copied to clipboard

Challenge: Form-like document understanding is a key yet under-investigated problem . endlessly training specialized models on new document types is not scalable in many practical scenarios.
Approach: They propose to use large-scale query-entity pairs generated from form-like webpages to pre-train QueryForm.
Outcome: The proposed framework sets state-of-the-art average F1 score on XFUND and Payment benchmarks.
Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to select demonstration examples for in-context learning are based on token embeddings.
Approach: They propose an algorithm to select demonstration examples for in-context learning of a query set . they use gradients of the output taken in the input embedding space to estimate model outputs .
Outcome: The proposed algorithm outperforms existing methods based on token embeddings by 11% . it scales up subset selection that would otherwise run full inference by 37.7 on models with 34 billion parameters .

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