3 papers
cs.CL2026
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…
cs.CR2026
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…
cs.LG2026
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…