6 papers
When Absence Is Evidence: Evaluating Completeness-Sensitive Negative Reasoning in Large Language Models
Byoungjae Min, Kennedy Edemacu, Sae-Hong Cho +3
Large language models (LLMs) are often asked whether something is absent from a record, list, or retrieved context. Yet non-observation licenses a negative answer only when evidenc…
DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents
Jong Wook Kim, Byoungjae Min, Kennedy Edemacu +3
Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never s…
Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs
Kennedy Edemacu, Mohammad Mahdi Shokri, Vinay M. Shashidhar +1
This work introduces PAS -- Privacy Anchor Substitution, a structured mechanism for enabling user location privacy in spatial retrieval-augmented generation (RAG) systems. Unlike c…
Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation
Kennedy Edemacu, Vinay M. Shashidhar, Micheal Tuape +3
Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to boost the capabilities of large language models (LLMs) by incorporating external, up-to-date knowledge so…
Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation
Kennedy Edemacu, Mohammad Mahdi Shokri
Retrieval-augmented generation (RAG) has emerged as a powerful paradigm for enhancing multimodal large language models by grounding their responses in external, factual knowledge a…
Fair In-Context Learning via Latent Concept Variables
Karuna Bhaila, Minh-Hao Van, Kennedy Edemacu +3
The emerging in-context learning (ICL) ability of large language models (LLMs) has prompted their use for predictive tasks in various domains with different data types, including t…