5 papers
LIME-LLM: Probing Models with Fluent Counterfactuals, Not Broken Text
George Mihaila, Suleyman Olcay Polat, Poli Nemkova +3
Local explanation methods such as LIME (Ribeiro et al., 2016) remain fundamental to trustworthy AI, yet their application to NLP is limited by a reliance on random token masking. T…
Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLP
Poli Nemkova, Amrit Adhikari, Matthew Pearson +2
Humanitarian organizations face a critical choice: invest in costly commercial APIs or rely on free open-weight models for multilingual human rights monitoring. While commercial sy…
Synthetic Adaptive Guided Embeddings (SAGE): A Novel Knowledge Distillation Method
Suleyman Olcay Polat, Poli A. Nemkova, Mark V. Albert
Model distillation enables the transfer of knowledge from large-scale models to compact student models, facilitating deployment in resource-constrained environments. However, conve…
Towards Automated Situation Awareness: A RAG-Based Framework for Peacebuilding Reports
Poli A. Nemkova, Suleyman O. Polat, Rafid I. Jahan +4
Timely and accurate situation awareness is vital for decision-making in humanitarian response, conflict monitoring, and early warning and early action. However, the manual analysis…
Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecasting
Apollinaire Poli Nemkova, Sarath Chandra Lingareddy, Sagnik Ray Choudhury +1
Large Language Models (LLMs) have shown impressive performance across natural language tasks, but their ability to forecast violent conflict remains underexplored. We investigate w…