Papers by Catherine Liu

2 papers
The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces (2026.acl-srw)

Copied to clipboard

Challenge: Large Language Models (LLMs) have unprecedented capabilities, but they pose security concerns . current adversarial attacks exploit vulnerabilities in the embedding space of language models, allowing attackers to bypass safety guardrails and cause significant harmful consequences.
Approach: They propose to use topological data analysis to characterize how adversarial perturbations act on text inputs by computing persistent homology metrics from attention maps across different model architectures.
Outcome: The proposed visualizations show that adversarial perturbations alter higher-dimensional topological features in ways that distinguish them from clean, non-adversarial inputs.
Annotating Interruption in Dyadic Human Interaction (2022.lrec-1)

Copied to clipboard

Challenge: Existing interruption and turn switch classification methods are not yet available.
Approach: They propose a new interruption annotation schema that integrates existing interruption and turn switch classification methods to annotate different types of interruptions.
Outcome: The proposed method can distinguish smooth turn exchange, backchannel and interruption (including interruption types) and to annotate dyadic conversation.

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