Papers by Emily K. Vraga

2 papers
BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing detection approaches struggle to balance content verification with knowledge modification under collapsed attention geometries.
Approach: They propose a dual-head reasoning framework that disentangles content-internal reasoning from knowledge-augmented reasoning.
Outcome: The proposed model outperforms detection approaches and provides interpretable diagnostics on when and why knowledge matters.
The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection (2025.emnlp-main)

Copied to clipboard

Challenge: a survey examines the interplay between factual accuracy and cognitive biases . misinformation is more than just the existence of incorrect information, it also entails complex relationships between the information and the entities that consume it.
Approach: They examine the interplay between traditional fact-checking and psychological concepts such as cognitive biases, social dynamics, and emotional responses.
Outcome: The findings highlight limitations of current methods and identify opportunities for improvement . they also outline future research directions to create more robust frameworks .

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