← Search

Arpita Vats

2 accepted papers

2025

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

EMNLP 2025

Alignment is no longer a luxury; it is a necessity. As large language models (LLMs) enter high-stakes domains like education, healthcare, governance, and law, their behavior must reliably reflect human-aligned values and safety constraints. Yet current evaluations rely heavily on behavioral proxies

2024

Recovering from Privacy-Preserving Masking with Large Language Models

ICASSP 2024accepted

Model adaptation is crucial to handle the discrepancy between proxy training data and actual users’ data received. To effectively perform adaptation, textual data of users is typically stored on servers or their local devices, where downstream natural language processing (NLP) models can be directly…

Cited by 0SourceScholar
Arpita Vats — accepted AI-conference papers · AIConfPaper