Sara Vera Marjanovic — accepted AI-conference papers

2025

A Reality Check on Context Utilisation for Retrieval-Augmented Generation

Lovisa Hagström, Sara Vera Marjanovic, Haeun Yu, Arnav Arora, Christina Lioma, Maria Maistro +2

ACL 2025long

Retrieval-augmented generation (RAG) helps address the limitations of parametric knowledge embedded within a language model (LM). In real world settings, retrieved information can vary in complexity, yet most investigations of LM utilisation of context has been limited to synthetic text. We introduc…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models

Sara Vera Marjanovic, Haeun Yu, Pepa Atanasova, Maria Maistro, Christina Lioma, Isabelle Augenstein

EMNLP 2024finding

Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge. However, conflicting knowledge can be present in the LM’s parameters, termed intra-memory conflict, which can…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗