7 papers
eval-unlearn: Benchmarking unlearning in Text-to-Image Diffusion Models
Mansi, Nikhil Raghavan, Zixia Huang +4
The rising number of concept unlearning techniques for text-to-image (T2I) diffusion models has produced a fragmented evaluation landscape. Methods are assessed under heterogeneous…
Certifying Concept Unlearning in Text-to-Image Diffusion Models
Mansi, Luca Marzari, Francesco Leofante
Existing evaluations of concept unlearning in text-to-image (T2I) diffusion models primarily rely on attack success rates obtained through automated adversarial prompt search. Howe…
Efficient bias mitigation in T2I diffusion models using Concept Graphs
Mansi, Avinash Kori, Francesco Leofante
Text-to-Image diffusion models often propagate harmful bias inherited from the training data. Existing bias mitigation techniques typically intervene only at the text encoder or pr…
Neurosymbolic Learning for Inference-Time Argumentation
Gabriel Freedman, Adam Dejl, Adam Gould +4
Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or conflicting, uncertain answe…
Selective Fine-Tuning for Targeted and Robust Concept Unlearning
Mansi, Avinash Kori, Francesca Toni +1
Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihoo…
Understanding Dementia Speech Alignment with Diffusion-Based Image Generation
Mansi, Anastasios Lepipas, Dominika Woszczyk +2
Text-to-image models generate highly realistic images based on natural language descriptions and millions of users use them to create and share images online. While it is expected…
AmalREC: A Dataset for Relation Extraction and Classification Leveraging Amalgamation of Large Language Models
Mansi, Pranshu Pandya, Mahek Bhavesh Vora +2
Existing datasets for relation classification and extraction often exhibit limitations such as restricted relation types and domain-specific biases. This work presents a generic fr…