3 papers
cs.CL2026
From Generation to Detection: Exploration of Discourse Driven Scenario based LLM Generated Fake News
Zeynep Özdemir, Murat Osmanoğlu, Sevgi Yiğit-Sert +2
In this study, we examine how modern LLMs generate and detect fake news under controlled settings across four manipulation scenarios. These are open-ended generation, rewriting, ma…
cs.LG2026
RecallRisk-BERT: A Multi-Task Framework for Post-Report Medical Device Recall Triage
Ali Semih Atalay, Sevgi Yigit-Sert
Medical device recalls are a critical regulatory mechanism for protecting patient safety. The growing volume of FDA recall records presents challenges in post-report recall triage,…
cs.CL2026
Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval
Sevgi Yigit-Sert
Retrieval-Augmented Generation (RAG) is widely used to improve the factual reliability of large language models (LLMs) by grounding answers in retrieved evidence. In misinformation…