5 papers
Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation
Li Siyan, Zhou Yu, Julia Hirschberg
Recent work on protecting privacy during user-LLM interactions often focuses on direct, explicit identifiers: the personally-identifiable information (PII) captured by standard det…
Read to Hear: A Zero-Shot Pronunciation Assessment Using Textual Descriptions and LLMs
Yu-Wen Chen, Melody Ma, Julia Hirschberg
Automatic pronunciation assessment is typically performed by acoustic models trained on audio-score pairs. Although effective, these systems provide only numerical scores, without…
Adaptable Non-parametric Approach for Speech-based Symptom Assessment: Isolating Private Medical Data in a Retrieval Datastore
Yu-Wen Chen, Julia Hirschberg
The automatic assessment of health-related acoustic cues has the potential to improve healthcare accessibility and affordability. Although parametric models are promising, they fac…
PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles
Li Siyan, Vethavikashini Chithrra Raghuram, Omar Khattab +2
Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user's machine, alleviat…
PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent
Jiateng Liu, Lin Ai, Zizhou Liu +6
Propaganda plays a critical role in shaping public opinion and fueling disinformation. While existing research primarily focuses on identifying propaganda techniques, it lacks the…