COVID-19 literature 1discourse analysis 1ideological bias 1retrieval-augmented generation 1sampling temperature 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?
Elmira Salari, Hazem Amamou, José Victor de Souza +3
The paper investigates how the sampling temperature of large language models influences the transfer of ideological discourses from retrieved COVID‑19 treatment articles in Retriev…
cs.CL2026
The Impact of Ideological Discourses in RAG: A Case Study with COVID-19 Treatments
Elmira Salari, Maria Claudia Nunes Delfino, Hazem Amamou +4
This paper studies the impact of retrieved ideological texts on the outputs of large language models (LLMs). While interest in understanding ideology in LLMs has recently increased…