collaborators

9 papers

cs.CL2026

What Drives LLM Self-Reflection? A Controlled Ablation of Uncertainty Routing in Armed Conflict Forecasting

Poli Nemkova, Haeshitha Indukuri

Self-reflection is widely assumed to improve LLM reasoning, yet which component drives the gain remains poorly understood. We present a controlled six-condition ablation isolating…

cs.CY2026

The Limits of LLM Forecasting: Parametric Knowledge Gaps Across Conflict Zones

Poli Nemkova

Media coverage of armed conflict is deeply asymmetric: we document a 224 gap between the most and least covered conflict zones in English-language media across 22 countries…

cs.CY2026

Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good

Poli Nemkova, Haeshitha Indukuri, Jaedon Charles

Agentic AI systems are increasingly proposed for social-good domains, often invoking the United Nations Sustainable Development Goals (SDGs) as a vocabulary of global benefit. Yet…

cs.CL2026

NLP for Social Good: A Survey and Outlook of Challenges, Opportunities, and Responsible Deployment

Antonia Karamolegkou, Angana Borah, Eunjung Cho +30

Natural language processing (NLP) now shapes many aspects of our world, yet its potential for positive social impact is underexplored. This paper surveys work in ``NLP for Social G…

cs.CL2026

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…

cs.CL2025

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…